Index

Faisal Shafait
Professor
Department of Computing

School of Electrical Engineering and Computer Science (SEECS)
National University of Sciences and Technology (NUST)
NUST Campus H-12, Islamabad
Tel: 051-90852064
Email: faisal.shafait@seecs.edu.pk
Web: https://tukl.seecs.nust.edu.pk/members/faisal_shafait.html

Specialization:
OCR, Machine Learning, Computer Vision, Image Processing

Education:
PhD - Computer Engineering - TU Kaiserslautern - Germany - 2008

1 .
Multi-Dimensional Assessment Framework: An Interdisciplinary Education approach for Students and Teachers:

In today’s interconnected world, interdisciplinary education (ID) is essential for preparing individuals to tackle complex global challenges. This study evaluates the impact of interdisciplinary education on students and teachers by focusing on twelve key parameters: disciplinary knowledge, interdisciplinary integration, higher-order cognitive skills, curiosity and openness, respect and collabora...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2024
Status: Active
Advisor
Tahira Lashari [DoC]
Committee Members
Sidra Sultana [DoC] Farzana Jabeen [DoC]
Students
Syeda Urooj Fatima [MSCS-2K22]

2 .
Bridging the Gap: Transitioning from Native to Hybrid App Development with Minimal Business Disruption:

In the ever-evolving landscape of business app development, companies face the challenge of whether to update their existing apps, originally built using native methods, to a hybrid approach. Many organizations hesitate due to concerns about disrupting Business as Usual (BAU) operations and the potential impact on current implementations. This study delves into the feasibility and benefits of int...


Project Level: PG
Project Type: Thesis Knowledge Area: Platform-based Development
Year: 2024
Status: Active
Advisor
Bilal Ali [DoC]
Committee Members
Fahad Ahmed Satti [DoC] Syed Imran Ali [DoC]
Students
Hannan Arif [MSCS-2K20]

3 .
AI-Enhanced Secure Network for Drone Swarms Using SDN:

Securing a network is a critical task; however, when it comes to drone swarms, network disconnection, unauthorized connectivity, or even a slight glitch in the network can turn catastrophic. Many solutions have been designed for network security, including intrusion detection systems, advanced network monitoring, intrusion prevention systems, advanced cryptography, and AI-based security solutions...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2024
Status: Active
Advisor
Rizwan Ahmad [EE]
Committee Members
Salman Abdul Ghafoor [EE] Shams Qazi [DoC]
Students
Muahmmad Abdullah Anwar [MSCS-2K22]

4 .
Reinforcement Learning based collision avoidance for UAVs:

In the aftermath of an earthquake, navigating a disaster zone with traditional methods is
fraught with danger. Collapsed buildings, debris, and displaced survivors create an
unpredictable environment for search and rescue UAVs. Here, we explore a promising
solution: LiDAR-based collision avoidance using Reinforcement Learning (RL). LiDAR
provides real-time, 3D obstacle detection, while RL all...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2024
Status: Active
Advisor
Rizwan Ahmad [EE]
Committee Members
Shams Qazi [DoC] Salman Abdul Ghafoor [EE]
Students
Bakhtawar Iftikhar [MSAI-2K22]

5 .
A Comprehensive Study of Land Use and Land Cover Changes in Pakistan's Urban Centers:

Urbanization and its impact on land use represent critical facets of sustainable development, particularly in rapidly expanding regions such as Pakistan’s top ten most populous cities. This thesis presents a comprehensive investigation into the temporal evolution of land use and land cover (LULC) patterns in these urban centers over the past four decades. Leveraging an extensive temporal archive ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Moazam Fraz [DoC]
Committee Members
Fahad Ahmed Satti [DoC] Zuhair Zafar [DoC] Momina Moetesum [DoC]
Students
Nabeel Ahmed Khan [MSCS-2K22]

6 .
Intelligent URL Classification System :

Purpose of this work is to design and developing an Intelligent URL Classification System using Cutting-Edge Artificial Intelligence Algorithms for Enhanced Social Media, Marketing, and Cybersecurity Applications. The rapid growth of online content and web applications has led to an exponential increase in URLs, making it challenging to categorize and filter them efficiently. URL classification i...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2024
Status: Active
Advisor
Muhammad Zeeshan [DoC]
Committee Members
Hasan Tahir [DoC] Qaiser Riaz [DoC]
Students
Sidra [MSCS-2K21]

7 .
Fake Article Detection using Deep Learning :

In the current era of Natural Language Processing, countless
models of Fake News Detection can help in labelling whether the
news is true or false. However, the majority of those models tell by reading
the title only, not by reading the full article. While some models like
BERT are very popular choice for Fake News Detection, BERT can take
only 512 tokens and hence, cannot read and label ful...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Khuram Shahzad [DoC]
Committee Members
Syed Imran Ali [DoC] Momina Moetesum [DoC] Farzana Jabeen [DoC]
Students
Saad Mahmud Mirza [MSCS-2K22]

8 .
Network Forensics Investigation of Smart Home Apps:

The aim of this project is to explore the privacy and security of various smart home apps using different network forensics tools.


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Sana Qadir [DoC]
Committee Members
Hasan Tahir [DoC] Madiha Khalid [DoC]
Students
Zunaira Ayaz [MSIS-2K22]

9 .
Multi-modal Explanation Generation for Interpreting Deep Learning-based Medical Decision-making:

Artificial Intelligence is being applied to various application domains for critical decision-making. Healthcare is one such area with high-stake decision requirements. This thesis investigates the role and impact of different visual and textual explanation approaches used for clinical decision-making for chest X-rays. As the high performance deep learning models are generally black-box, therefor...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Syed Imran Ali [DoC]
Committee Members
Adnan Rashid [DoC] Bilal Ali [DoC] Muhammad Khuram Shahzad [DoC]
Students
Urooj Fatima [MSCS-2K22]

10 .
VLM-based Entity Recognition for Automated Vocational Knowledge Graph Population:

Vocational training plays a critical role in equipping individuals with the skills and knowledge necessary for specific careers, facilitating workforce development and economic growth. This research focuses on enhancing vocational training through the development of a Vocational Knowledge Graph (VKG) using Visual Language Models (VLMs). A VKG functions as a comprehensive encyclopedia of careers, ...


Project Level: PG
Project Type: Thesis Knowledge Area: Software Development Fundamentals
Year: 2024
Status: Active
Advisor
Fahad Ahmed Satti [DoC]
Committee Members
Syed Imran Ali [DoC] Bilal Ali [DoC] Muhammad Moazam Fraz [DoC]
Students
Ayesha Shehzadi [MSDS-2K22]

11 .
Mitigating Hallucination in Large Language Models to enhance Mental Health Support:

This research project delves into the manifestation of hallucination within Large Language Models (LLMs) and its consequential impacts on applications within the domain of mental health. The primary objective is to discern effective strategies for curtailing hallucinatory occurrences, thereby bolstering the dependability and security of LLMs in facilitating mental health interventions such as the...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2024
Status: Active
Advisor
Bilal Ali [DoC]
Committee Members
Syed Imran Ali [DoC] Shah Khalid [DoC]
Students
Abdul Muqtadir [MSCS-2K21]

12 .
Brain Tumor Detection and Classification using Deep Leraning:

Description:
This project aims to develop a system for the detection and classification of brain tumors using Convolutional Neural Network (CNN) and Deep Neural Network (DNN) algorithms. The system will analyze medical imaging data such as MRI scans to accurately identify the presence of tumors and classify them into different categories.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Shah Khalid [DoC]
Committee Members
Bilal Ali [DoC] Farzana Jabeen [DoC] Muhammad Khuram Shahzad [DoC]
Students
Muhammad Zubair Abid [MSAI-2K23]

13 .
Forecasting Global Horizontal Irradiance in Pakistan to Optime Solar Energy Output using Deep Learning Techniques:

Electricity plays a substantial role in the economic and technological growth of a country. The primary sources of electricity production are conventional fossil fuels across the globe. Fossil fuels are on the verge of extinction as they take many years to compose, and the existing reserves are being consumed much faster than the new fossil fuels being formed. In addition, fossil fuels are one of...


Project Level: PG
Project Type: Thesis Knowledge Area: Algorithms and Complexity
Year: 2024
Status: Active
Advisor
Arham Muslim [DoC]
Committee Members
Junaid Younas [DoC] Momina Moetesum [DoC]
Students
Muhammad Ali [MSDS-2K20]

14 .
Brain Tumor Detection and Classification using Deep Leraning:

Description:
This project aims to develop a system for the detection and classification of brain tumors using Convolutional Neural Network (CNN) and Deep Neural Network (DNN) algorithms. The system will analyze medical imaging data such as MRI scans to accurately identify the presence of tumors and classify them into different categories.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Shah Khalid [DoC]
Committee Members
Bilal Ali [DoC] Farzana Jabeen [DoC] Muhammad Khuram Shahzad [DoC]
Students
Aqsa Naseer [MSIT-2K22]

15 .
Automated Medical Report Generation through Knowledge Graph and Large Language Models:

Medical Report Generation (MRG) is gaining attention in Natural Language Generation (NLG) research. In clinics, medical reports are crucial for guiding patient treatment. However, creating reports can be time-consuming for experienced radiologists and prone to errors for inexperienced ones. A more efficient reporting method is needed to handle the healthcare workload while maintaining patient dat...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2024
Status: Active
Advisor
Fahad Ahmed Satti [DoC]
Committee Members
Syed Imran Ali [DoC] Bilal Ali [DoC] Rabia Irfan [DoC]
Students
Maira Sohail [MSCS-2K21]

16 .
ENABLING TRANSFER LEARNING FOR IMPROVED GENERALIZATION IN EXPLAINABLE REINFORCEMENT LEARNING FOR DRUG REPURPOSING:

Exploring new uses for existing drugs is a key focus in healthcare research today. This thesis dives into drug repurposing, aiming to find fresh ways to utilize known medications. By employing adaptable transfer learning techniques in reinforcement learning, we're striving to change the approach to drug discovery. Through careful study and innovative methods, we aim to make significant improvemen...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Khuram Shahzad [DoC]
Committee Members
Momina Moetesum [DoC] Farzana Jabeen [DoC]
Students
Anam Zulfiqar [MSCS-2K23]

17 .
Enhanced Deep Learning Techniques for Road Crack Detection and Segmentation:

Monitoring the structural health of roads constitutes a vital aspect in facilitating the inspection of transportation infrastructure. This study uses deep learning methodologies for detecting cracks in road images, presenting an automated approach for semantic segmentation of road crack images at the pixel level, using transformer-based techniques. The methodology consists of selecting an appropr...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Mohsin Kamal [EE]
Committee Members
Muhammad Imran [EE] Hafsa Iqbal [EE] Rizwan Ali Naqvi [ECM]
Students
Kiran Shakeel [MSCS-2K21]

18 .
From Sequences to Functions: A Machine Learning Odyssey in Peptide Classification:

Peptides, the fundamental building blocks of proteins, play a pivotal role in the biological mechanisms of living organisms. Known as the powerhouses of cellular function, proteins' biological roles and intricate mechanisms can only be fully understood through an in-depth exploration of peptides. These short chains of amino acids are not only crucial for understanding protein function but are als...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Muhammad Nabeel Asim [ECM] Muhammad Naseer Bajwa [DoC]
Students
Sarfraz Ahmad [MSDS-2K21]

19 .
Layout detection of textual documents using Deep Leaning:

Layout detection is a well-known task in the document AI domain. The target of layout detection is to extract and categorise the content of digital and scanned documents. For example, if we take a research paper and feed its contents to train an LLM for some downstream task, the raw text in Markdown or Latex format can sometimes be very difficult to build structure from. Layout detection can help...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Naseer Bajwa [DoC]
Committee Members
Junaid Younas [DoC] Muhammad Imran Malik [DoC]
Students
Mohammad Muddassir Mehmood [MSAI-2K21]

20 .
Table Structure Recognition from heterogenous documents using deep learning:

Table structure recognition is one of the most well-researched areas in the document AI domain, yet there are not many open-source solutions available that may be readily used. These document AI tasks are considered difficult therefore AWS and GCP have their online APIs to provide these services and charge per document processed. Tables are complex structures for compact data representations. How...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Naseer Bajwa [DoC]
Committee Members
Junaid Younas [DoC] Muhammad Imran Malik [DoC]
Students
Saeed Ahmed [MSAI-2K21]

21 .
Deciphering Digital Dialogues: A Deep Learning Framework for Discourse Analysis in German:

To curb the spread of hate content on social media, ongoing research focuses on AI-driven computational predictors. However, the diversity of languages poses a challenge, hindering the development of universally applicable predictors for accurate identification. While widely spoken languages have dedicated predictors, less common languages like German lack robust solutions. Current predictors for...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Muhammad Nabeel Asim [ECM] Muhammad Naseer Bajwa [DoC]
Students
Momina Ahsan [MSDS-2K21]

22 .
Lung CXR Abnormality Detection: Interpretable Insights from Bayesian Neural Networks":

The detection of abnormalities in lung CXR (chest X-ray) images is critical for early diagnosis and effective management of respiratory diseases. The current thesis aims at developing an interpretable and explainable Bayesian Neural Network (BNN) model tailored specifically for abnormality detection in lung CXR images. By leveraging Bayesian inference, the model is supposed to offer probabilistic...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Junaid Younas [DoC] Muhammad Naseer Bajwa [DoC]
Students
Javeria Khalid [MSCS-2K20]

23 .
Enhanced IoT Security: Intelligent Anomaly Detection and Encryption at the Edge:

Ensuring the security of IoT devices against adversarial attacks is paramount in today's interconnected world. However, traditional methods for detecting breaches may fall short in identifying evolving attack techniques. Hence, there arises a necessity to develop an intelligent edge security solution that harnesses the power of Machine Learning (ML) anomaly detection algorithms. This solution sho...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Mohsin Kamal [EE]
Committee Members
Wajid Mumtaz [EE] Madiha Khalid [DoC]
Students
Hamza Sohail [MSCS-2K21]

24 .
Automated Code Generation for Real-Time Monitoring of Warehouse Facilities:

This research proposes developing a dynamic automated code generation system tailored for real-time monitoring of warehouses and cargo storage facilities. The system aims to streamline the collection of data from sensors and IoT devices installed in various areas of these facilities, capturing crucial metrics such as temperature, humidity, and unauthorized access incidents. By employing automated...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Nazia Perwaiz [DoC]
Committee Members
Sidra Sultana [DoC] Tahira Lashari [DoC]
Students
Usama Saddique [MSDS-2K21]

25 .
Unlocking Logistics Innovation: Automated Research Review Platform Utilizing Generative AI and NLP:

This study looks at how Generative AI can be used in the logistics industry. The main aim is to create a system that automatically reviews research papers for people who work in research and practice. This system will help them go through lots of academic papers quickly. By using Generative AI and Natural Language Processing (NLP), the system will make the literature review process faster and eas...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Nazia Perwaiz [DoC]
Committee Members
Sidra Sultana [DoC] Tahira Lashari [DoC]
Students
Dur-E-Shahwar Zahra Tallat [MSDS-2K21]

26 .
Driver Behavior Analysis for Safety Enhancement:

Driver Behavior Analysis for Safety Enhancement presents a promising avenue for research, aiming to leverage cutting-edge technologies such as computer vision and machine learning to improve road safety in logistics operations. By analyzing data from cameras installed in vehicles and/or in vehicle sensors, this research can delve into identifying and mitigating risky driving behaviors, such as di...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Nazia Perwaiz [DoC]
Committee Members
Sidra Sultana [DoC] Muhammad Moazam Fraz [DoC]
Students
Muhammad Naveed [MSDS-2K21]

27 .
Mapping the Path to Freezing of Gait in Parkinson's: A Deep Wearable Exploration:

Freezing of Gait (FoG) stands as a prevalent symptom of Parkinson's disease (PD), presenting a clinical challenge where individuals experience a temporary inability to initiate or continue walking, disrupting the natural gait cycle. These episodes often precipitate falls and pose a risk of injuries, significantly compromising the affected individual's independence in daily activities and overall ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Qaiser Riaz [DoC]
Committee Members
Mehdi Hussain [DoC] Muhammad Zeeshan [DoC]
Students
Seemab Khaliq [MSIT-2K21]

28 .
Unwrapping the Fortresses: An Exploration of Financial Institution Information Security in USA, Europe, and Pakistan:

This research delves into the intricate dynamics of regulatory frameworks, compliance standards, and financial transformations within the banking and financial sectors across Pakistan, Europe, and the USA. Through a meticulous examination of regulatory landscapes and compliance standards, including the Payment Card Industry Data Security Standard (PCIDSS) and regulatory acts such as the Bank Secr...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Hasan Tahir [DoC]
Committee Members
Muhammad Aleem [ECM] Mehdi Hussain [DoC]
Students
Muhammad Atif Hameed [MSIS-2K21]

29 .
Repeater jamming suppression method on Identity recognition and chaotic encryption:

A repeater jamming suppression method for a PD fuze based on identity (ID) recognition and chaotic encryption


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Shams Qazi [DoC]
Committee Members
Rizwan Ahmad [EE] Mehdi Hussain [DoC]
Students
Rida Ashfaq [MSIS-2K22]

30 .
"Enhancing Psycho Social Behavioral skills for Autism Spectrum Disorder: Evaluating a Multimodal Learning Game Framework for Smart Devices":

Differently-abled individuals face challenges when it comes to accessing and using mobile devices. Many existing applications are not designed with the needs of these users in mind, which can lead to frustration and a lack of engagement. In particular, visually impaired users may have difficulty accessing visual content, while users with mobility impairments may have difficulty using traditional ...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2024
Status: Active
Advisor
Farzana Jabeen [DoC]
Committee Members
Tahira Lashari [DoC] Ayesha Habib [ECM] Mehvish Rashid [DoC]
Students
Fatima Batool [MSDS-2K22]

31 .
Advancing AI Literacy for 21st-Century Education: A Framework for Integrating AI Skillsets in education using STEAM approach:

Advancing AI literacy in 21st-century education is critical for preparing students to navigate a technology-driven world. This research introduces a comprehensive framework for integrating AI skillsets into education using a STEAM (Science, Technology, Engineering, Arts, and Mathematics) approach. The framework aims to provide a flexible and user-friendly tool for educators to incorporate AI conc...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2024
Status: Active
Advisor
Arham Muslim [DoC]
Committee Members
Tahira Lashari [DoC] Sara Tariq [ECM]
Students
Muhammad Nauman Khan [MSITL-2K22]

32 .
Gamified Learning in the Metaverse: Enhancing School-level Students' Conceptual Grasp of Mathematical Topics:

This thesis aims to investigate the impact of gamified learning in the Metaverse on school-level students' conceptual grasp of mathematical topics. Objectives include examining the role of gamified experiences in enhancing understanding, evaluating the design and acceptance of innovative technologies, and proposing a theory-based design for improving mathematical conceptual understanding among st...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2024
Status: Active
Advisor
Arham Muslim [DoC]
Committee Members
Sara Tariq [ECM] Sohail Iqbal [DoC]
Students
Bushra Abad [MSITL-2K20]

33 .
A machine learning approach for active S-Box analysis and prediction:

S-Boxes, also known as substitution boxes, play a vital role in cryptographic algorithms, particularly within block ciphers. The security of cryptographic systems is significantly influenced by the design and type of S-Boxes. Various methods have been proposed to enhance the strength and resistance of S-Boxes against attacks. Generally, the evaluation of S-Box strength or weakness is determined t...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Mehdi Hussain [DoC]
Committee Members
Madiha Khalid [DoC] Naveed Riaz [DoC]
Students
Usama Musadiq [MSIS-2K22]

34 .
Automated landmark detection for cephalometric radiographs analysis:

Cephalometric radiographs are taken by orthodontists to quantitatively evaluate the skeletal relationship between the cranial base and the maxilla or mandible, the relationship between maxilla and mandible, and the dentoalveolar relationship. They also serve for determining the growth pattern through quantitative and qualitative evaluations and superimposition of serial radiographs. Moreover, cep...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Muhammad Moazam Fraz [DoC]
Committee Members
Muhammad Anwaar Khalid [ECM] Zuhair Zafar [DoC] Syed Imran Ali [DoC]
Students
Reeha Khan [MSDS-2K22]

35 .
Dynamic Trust Management for Industrial IoT:

Industry 4.0 has revolutionized the way manufacturing factories functopm. Smart factories utilize advanced sensors and robotics to collect and analyze data from various stages of the manufacturing process. However, security continues to be a major concern in the adoption of Internet of Things (IoT) in industrial processes. It is necessary to protect industrial data contained in IIoT devices and t...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2024
Status: Active
Advisor
Hasan Tahir [DoC]
Committee Members
Muhammad Zeeshan [DoC] Farzana Jabeen [DoC]
Students
Muhammad Khuram Ashraf [MSIS-2K21]

36 .
A Metalinguistic Vocabulary Initiative: A Padlet - Powered Solution for revolutionizing language skills :

Metalinguistic vocabulary includes the ability where one understands that language has the potential to go beyond the literal meanings or further include multiple or implied meanings or figurative meaning of words and expressions. It is important because it allows individuals to discuss, analyze and manipulate language consciously. For empowering this skill (where students can go beyond mere wor...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2024
Status: Active
Advisor
Tahira Lashari [DoC]
Committee Members
Mehvish Rashid [DoC] Sidra Sultana [DoC]
Students
Bakhtawar Hayat [MSITL-2K20]

37 .
Title: Detection of Panic Attacks Using Machine Learning Models:

The current landscape of panic attack detection is characterized by subjective assessment methods, leading to delayed intervention and limited accuracy. Existing approaches often rely on singular modalities, resulting in inadequate sensitivity and specificity. Additionally, the absence of standardized criteria for panic attack classification poses a barrier to the development of universally appli...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2024
Status: Active
Advisor
Farzana Jabeen [DoC]
Committee Members
Tahira Lashari [DoC] Mehvish Rashid [DoC] Sidra Sultana [DoC]
Students
Muhammad Rehan Ghafoor [MSIT-2K20]

38 .
Automated detection of Glaucoma Using SegNet and Ensemble Learning:

In recent strides within glaucoma research, deep learning has emerged as a promising tool for timely detection to mitigate the worsening effects of the condition. However, challenges persist, primarily stemming from the limited availability of data, compromising the effectiveness of training in existing deep learning frameworks. Additionally, the constraints imposed by smaller datasets contribute...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Farzana Jabeen [DoC]
Committee Members
Mehvish Rashid [DoC] Tahira Lashari [DoC] Zuhair Zafar [DoC]
Students
Ayesha Naeem [MSIT-2K20]

39 .
Cattle Farming Activity Monitoring Using Advance Deep learning Approach:

Precision livestock farming is a type of agriculture that uses technology to monitor and manage livestock, with the goal of improving efficiency, productivity, and animal welfare. One way to do this is through the use of image processing techniques, such as segmentation and contour extraction, to identify and track individual animals.In this work, an instance segmentation technique based on Mask ...


Project Level: PG
Project Type: Thesis Knowledge Area: Algorithms and Complexity
Year: 2024
Status: Active
Advisor
Muhammad Shahzad Younis [EE]
Committee Members
Arbab Latif [EE] Wajid Mumtaz [EE]
Students
Muhammad Asim [MSIT-2K20]

40 .
Judicial Automation in Pakistan using AI:

This project aims to understand and revolutionize the legal landscape by implementing artificial intelligence to streamline and enhance judicial processes. Through advanced automation, the system aims to optimize case management, legal research, and document analysis, ultimately expediting court proceedings. By harnessing AI technologies, such as natural language processing and machine learning, ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Naseer Bajwa [DoC] Rabia Irfan [DoC]
Students
Baria Mubashar Mirza [MSAI-2K21]

41 .
Hybridized Legal Document Summarization: Integrating NER, Extractive, and Abstractive Techniques for Enhanced Results:

The aim of this research project is to explore a novel approach to the summarization of legal documents. This research delves into the innovative integration of Named Entity Recognition (NER), extractive summarization, abstractive techniques, and chunking methods. The methodology begins with NER to extract key entities, followed by a combination of extractive and abstractive summarization techniq...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Seemab Latif [DoC] Rabia Irfan [DoC]
Students
Mishal Ashraf [MSAI-2K21]

42 .
Adversarial Attacks on Signature Verification: Exploring GAN-Generated Signatures and Vulnerabilities:

Our objective in this thesis is to investigate the vulnerability of the offline signature verification system by attempting to deceive it with generated offline signatures. With the progress of Generative Adversarial Networks (GANs), genuine signatures can be accurately replicated. Studies have demonstrated how GANs can augment the signature dataset, leading to an enhancement in the overall accur...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Junaid Younas [DoC] Momina Moetesum [DoC]
Students
Haider Ali [MSAI-2K22]

43 .
Adversarial Attacks on Signature Verification: Exploring GAN-Generated Signatures and Vulnerabilities:

Our objective in this thesis is to investigate the vulnerability of the offline signature verification system by attempting to deceive it with generated offline signatures. With the progress of Generative Adversarial Networks (GANs), genuine signatures can be accurately replicated. Studies have demonstrated how GANs can augment the signature dataset, leading to an enhancement in the overall accur...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Junaid Younas [DoC] Momina Moetesum [DoC]
Students
Haider Ali [MSAI-2K22]

44 .
Semantic Segmentation of Forest Regions from Satellite Imagery using Transformers:

This project aims to employ artificial intelligence techniques, including machine learning algorithms and remote sensing data analysis, to enhance forest regions segmentation. By utilizing latest deep learning methods like transformers, the system will develop predictive models capable of detection and accurate segmentation of forest regions. The implementation of AI in forest region segmentation...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Momina Moetesum [DoC] Muhammad Ali Tahir [ECM]
Students
Nermeen Shah [MSEE-2K20]

45 .
Leukemia Cancer Classification using Micro Gene Array Dataset:

Leukemia, a complex and heterogeneous group of blood cancers, presents a significant challenge in accurate diagnosis and classification due to its diverse genetic profiles. Traditional methods of leukemia classification based on microscopic examination and clinical parameters often lack precision and fail to capture the intricate molecular variations associated with the disease. With the advent o...


Project Level: PG
Project Type: Thesis Knowledge Area: Computational Science
Year: 2024
Status: Active
Advisor
Sidra Sultana [DoC]
Committee Members
Nazia Perwaiz [DoC] Farzana Jabeen [DoC] Tahira Lashari [DoC]
Students
Syyeda Shifa Fatima [MSIT-2K20]

46 .
Enhancing Multimodal Information Extraction from Visually Rich Documents :

Visually rich documents (VRDs), such as forms, invoices, receipts, and ID cards, are ubiquitous in daily business and life. Automatically understanding VRDs can greatly facilitate the key information entry, retrieval and compliance check in enormous and various applications, including file understanding in court trial, contract checking in the business system, statements analysis in accounting or...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2024
Status: Active
Advisor
Momina Moetesum [DoC]
Committee Members
Faisal Shafait [DoC] Adnan Ul-Hasan [ECM] Junaid Younas [DoC]
Students
Aresha Arshad [MSDS-2K22]

47 .
Addressing the Non-Differentiability in ReLU through a Smooth Polynomial Approximation to Enhance ReLU's Performance in Image Classification Problems:

Neural Networks rely heavily on Activation Functions. These functions determine how the network responds to its inputs and how it learns. Traditional activation functions, such as the rectified linear unit (ReLU) and the exponential linear unit (ELU), are effective for many tasks. However, they also have some drawbacks. For example, ReLU, the most commonly used function, is non-differentiable at ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Zuhair Zafar [DoC]
Committee Members
Bilal Ali [DoC] Muhammad Khuram Shahzad [DoC]
Students
Janita Khan [MSCS-2K22]

48 .
Predictive Attribute Learning: From 2D RGB Prediction to Temporal Dynamics:

This project focuses on leveraging advanced machine learning techniques to predict RGB values of objects, transcending from 2D image predictions to understanding temporal dynamics in a sequence of frames. Inspired by NERF's novel approach to scene reconstruction, our work diverges to concentrate solely on learning intricate geometry through RGB value prediction. Our algorithm utilizes a fully-con...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Adnan Aslam [BS]
Committee Members
Muhammad Khuram Shahzad [DoC] Bilal Ali [DoC]
Students
Muhammad Haider [MSCS-2K20]

49 .
Improving Performance of Intrusion Detection Systems using Machine Learning Techniques:

With the increase in the usage of the Internet, a large amount of information is exchanged between different communicating devices. The data should be communicated securely between the communicating devices and therefore, network security is one of the dominant research areas for the current network scenario. Intrusion detection systems (IDSs) are therefore widely used along with other security m...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Syed Imran Ali [DoC]
Committee Members
Bilal Ali [DoC] Fahad Ahmed Satti [DoC]
Students
Amna Zahid [MSIT-2K20]

50 .
Secure Ledger Technologies: A Barrier Against Financial Illegitimacy:

Addressing the issue necessitates exploring the potential of blockchain technology to revolutionize anti-money laundering efforts while upholding privacy rights and regulatory compliance.


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2023
Status: Active
Advisor
Huma Ghafoor [EE]
Committee Members
Sana Qadir [DoC] Syed Ali Hassan [EE]
Students
Shamama Tul Amber [MSIS-2K22]

51 .
Active Analysis of Encrypted Traffic Flows for Application Fingerprinting:

The rapid adoption of network encryption has introduced new challenges in identifying and understanding the behaviors of applications communicating over encrypted channels. Traditional passive analysis techniques are often insufficient to gain a comprehensive understanding of how applications respond to adversarial conditions. This project aims to explore active techniques for analyzing encrypted...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2023
Status: Active
Advisor
Mehdi Hussain [DoC]
Committee Members
Qaiser Riaz [DoC] Naveed Riaz [DoC]
Students
Shaher Bano [MSIS-2K22]

52 .
Advancing fabric defect detection in real-world manufacturing using deep learning:

Fabric defect detection is a critical aspect of ensuring quality control within the textile manufacturing industry. While manual inspection has traditionally been the norm, the adoption of automatic defect detection schemes based on deep learning models offers a timely and efficient solution for addressing production-related issues and assessing fabric quality. Although significant research has b...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Rafia Mumtaz [DoC]
Committee Members
Tahira Lashari [DoC] Muhammad Daud Abdullah Asif [DoC]
Students
Mariam Nasim [MSDS-2K22]

53 .
Detection of Ransomware-like Data Manipulation in Android Applications:

Ransomware is one of the malicious software created by the bad guys. The purpose of this malware is to encrypt, obfuscate, encode or make the victim’s data inaccessible. Once victim’s data is made inaccessible, attacker demands ransom in order to decrypt, decode or make the victim’s data accessible again. Some ransomware even threaten the victim to sell the data in black market in case of failure...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2023
Status: Active
Advisor
Mehdi Hussain [DoC]
Committee Members
Hasan Tahir [DoC] Naveed Riaz [DoC]
Students
Muhammad Sibtain [MSIS-2K22]

54 .
On Shadow Removal from Images:

This research introduces a novel method for shadow removal from images utilizing Generative Adversarial Networks (GANs). GANs, a form of deep learning technology, are used to train a model, capable of detecting and removing shadows from various images accurately. This method supersedes traditional shadow removal techniques by providing high-quality results unsupervised, maintaining the integrity ...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2023
Status: Completed
Advisor
Ahmad Salman [EE]
Committee Members
Seemab Latif [DoC] Salman Abdul Ghafoor [EE]
Students
Bisma Ahmad [MSDS-2K21]

55 .
Automatic Classification of Marine Vessels using Acuostic Data:

Underwater acoustic classification is a key area of research. Such classification can be used to predict/identify the marine vessels from the emitted acoustic signals. It has various applications in military, commercial and environmental domains. The success of artificial intelligence based methods in various similar areas inspired the research community to explore artificial intelligence based m...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Qaiser Riaz [DoC]
Committee Members
Muhmmad Irfan [ECM] Mehdi Hussain [DoC] Hasan Tahir [DoC]
Students
Hina Qasim [MSIT-2K20]

56 .
An Efficient Smart Car Parking System using Machine Learning based on iFogSim:

Fog computing helps the devices present on the internet to make decisions on the edge
nodes. Edge nodes are comprised of a cluster of smaller nodes which are basically known as sensors. These sensors are responsible for sending the data to the edge node continuously or after some time. This data is processed according to the given application in the edge nodes and processed data is sent to the m...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2023
Status: Completed
Advisor
Muhammad Khuram Shahzad [DoC]
Committee Members
Rabia Irfan [DoC] Momina Moetesum [DoC] Syed Imran Ali [DoC]
Students
Muhammad Fasih Ashfaq [MSDS-2K20]

57 .
Deep Learning based Traffic Surveillance for Precise Road Maintenance Prediction using Load Analysis:

The maintenance and upkeep of road infrastructure plays a critical role in ensuring safe and efficient transportation systems. Roads experience varying levels of stress due to the traffic they bear, causing damage over time. Predicting the optimal timing for road maintenance is very important to stop the infrastructure from getting worse, reduce repair costs, and minimize disruptions to daily com...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Rabia Irfan [DoC]
Committee Members
Muhammad Naseer Bajwa [DoC] Momina Moetesum [DoC]
Students
Muhammad Sohail Abbas [MSCS-2K20]

58 .
Unveiling Neuroimaging-Based Biomarkers: Using Deep Neural Networks to Predict Brain Age and Assess Cognitive Health:

Deep neural networks exhibit a significant capability in accurately predicting the chronological age of individuals without health issues through the analysis of neuroimaging data. This anticipated brain age, derived from neural network predictions, holds promise as a potential biomarker for identifying conditions linked to aging. Employing machine learning techniques on brain MRI data facilitate...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Muhammad Daud Abdullah Asif [DoC]
Committee Members
Rafia Mumtaz [DoC] Bilal Ali [DoC]
Students
Ayesha Khan [MSAI-2K22]

59 .
Gimkit: a gamification teaching approach for measuring digital learning assessment:

Many educational institutions transitioned from in-person learning to online learning. Teachers and professors were tasked with making significant changes to their teaching. For this purpose, Gimkit: a gamification teaching approach for measuring digital learning assessment will be used. Gamification is a teaching strategy that incorporates game aspects in order to encourage students to actively...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2023
Status: Active
Advisor
Tahira Lashari [DoC]
Committee Members
Sidra Sultana [DoC] Farzana Jabeen [DoC]
Students
Khadija Shafique [MSITL-2K20]

60 .
Evaluation of SAST and DAST tools for Web Application Security:

This research evaluates web application security using both Static Application Security Testing (SAST) and Dynamic Application Security Testing (DAST) tools. The aim is to rigorously compare the effectiveness and coverage of these industry-standard tools to identify, categorize and rank vulnerabilities. It also aims to assist developers and security professionals in making informed decisions to i...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2023
Status: Active
Advisor
Sana Qadir [DoC]
Committee Members
Ayesha Kanwal [DoC] Seema Jehan [DoC]
Students
Eman Waheed [MSIS-2K21]

61 .
Security Testing of Active Directory:

Microsoft Active Directory (AD) is one of the most commonly used Identity and Access Management (IAM) service providers. It has various applications, including user authentication and access management, because of which it forms the foundation of an organization’s cybersecurity. AD has, by default, certain misconfigurations and vulnerabilities that can lead to different cyberattacks (such as LLMN...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2023
Status: Active
Advisor
Sana Qadir [DoC]
Committee Members
Mehdi Hussain [DoC] Hasan Tahir [DoC]
Students
Muhammad zaeem Javed [MSIS-2K20]

62 .
Comparing the effects of individual and team participation in gamified lessons on assessment performance:

The advent of the COVID-19 pandemic brought about a swift transition to online teaching and learning with the widespread adoption of online education technologies including gamification of lessons. Gamification has been used by teachers as a tool to review basic concepts learnt by students in traditional as well as in flipped classrooms. This technology offers students the ability to participate ...


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2023
Status: Active
Advisor
Tahira Lashari [DoC]
Committee Members
Sidra Sultana [DoC] Farzana Jabeen [DoC]
Students
Fahad Ansari [MSIT-2K20]

63 .
Machine Unlearning for Image Data:

Machine unlearning is an emergent subfield of machine learning that aims to remove the influence of a specific subset of training examples — the "forget set" — from a trained model. Furthermore, an ideal unlearning algorithm would remove the influence of certain examples while maintaining other beneficial properties, such as the accuracy on the rest of the train set and generalization to held-out...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Momina Moetesum [DoC]
Committee Members
Seemab Latif [DoC] Muhammad Naseer Bajwa [DoC] Rabia Irfan [DoC]
Students
Javeria Tariq [MSCS-2K22]

64 .
Deep Learning based Malicious Traffic Detecting in IoT Network:

We intend to exploit capability of ML having self-learning algorithms to detect network attacks in computing environments of IoT. This study aim to investigate current up to date ML based intrusion detection patterns and propose efficient intrusion detection for IoT environments using deep learning. It will also consider resource constraints while planning and employing intrusion detection schem...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2023
Status: Completed
Advisor
Muhammad Zeeshan [DoC]
Committee Members
Qaiser Riaz [DoC] Hasan Tahir [DoC]
Students
Muhammad Imran Aziz [MSCS-2K20]

65 .
Few-Shot Learning with Large Language Models (LLMs):

The main objective of this research is to improve the few-shot learning capabilities of large language models, allowing them to generalize to new tasks with minimal or no task-specific training data.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Muhammad Daud Abdullah Asif [DoC]
Committee Members
Shams Qazi [DoC] Rafia Mumtaz [DoC]
Students
Najam Ahmed [MSAI-2K22]

66 .
Medical Image Segmentation using deep learning:

The main objective of this thesis is to develop a Deep learning based model capable of accurately segmenting medical images, such as identifying tumor boundaries in MRI scans. The research will involve exploring various GAN architectures, loss functions, and optimization techniques to achieve optimal performance in medical image segmentation tasks.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Muhammad Daud Abdullah Asif [DoC]
Committee Members
Hashir Moheed Kiani [DoC] Rafia Mumtaz [DoC]
Students
Ushnah Abbasi [MSAI-2K22]

67 .
Coral Classification in Unconstrained Underwater Imagery:

In this thesis, we aim to address the problem of coral classification in unconstrained underwater imagery which comes with the challenge of compromised vision due to water murkiness, turbidity and intra-class dissimilarity and inter-class similarity of coral species. We will device a dedicated deep neural network to tackle this challenge.


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2023
Status: Completed
Advisor
Ahmad Salman [EE]
Committee Members
Salman Abdul Ghafoor [EE] Wajid Mumtaz [EE]
Students
Lajvanti Ratnani [MSAI-2K21]

68 .
Single Image Super-Resolution using Real World Remote Sensing Imagery:

In the realm of remote sensing, the demand for improved spatial resolution has persisted across multiple domains despite the exponential rise in satellite images. Single Image Super-Resolution (SISR) aims to bridge this gap, and many state-of-the-art (SOTA) deep learning models have been utilized for this purpose. However, the generation of low-resolution (LR) image pairs from high-resolution (HR...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2023
Status: Active
Advisor
Muhammad Moazam Fraz [DoC]
Committee Members
Zuhair Zafar [DoC] Nazia Perwaiz [DoC] Bostan Khan [ECM]
Students
Usama Aleem Shami [MSCS-2K20]

69 .
Impact of employee training, motivation and competencies on work performance - A systematic case built using training needs assessment:

With an increase in talent and the acceptability of technology across the globe, Pakistan which is an emerging economy needs to produce better talent that suits the needs of the professional ecosystem. It is a well-known fact that Training and Development play a vital role in improving employee performance and commitment in an organization. However, the competency of an employee as per its tier i...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2023
Status: Active
Advisor
Arham Muslim [DoC]
Committee Members
Rida Sajjad [ECM] Jaudat Mamoon [DoC]
Students
Naila Kamran Chaudhry [MSITL-2K21]

70 .
Deep Packet Investigation using P4:

Programming Protocol independent Packet Processing (P4) framework enables network devices to get hold on data plane activities with full control and flexibility. P4 allows a user to program and define the packet processing pipeline of the forwarding elements in the software defined networks (SDN). P4 offers a full feature set for processing L2, L3 and L4 protocols header fields. It can only proce...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2022
Status: Active
Advisor
Salman Abdul Ghafoor [EE]
Committee Members
Arsalan Ahmad [DoC] Syed Taha Ali [EE] Ahmad Salman [EE]
Students
Azhar Hayat [MSIT-2K21]

71 .
Assistive Technology: Empowering Social Safety Skills of Autistic Children :

The rise in sexual abuse and abduction incidents has become a persistent societal problem in Pakistan. This requires a comprehensive as well as an inclusive response so that the vulnerable population can be protected. However, one of the most neglected groups of this population is autistic children. The statistics from South Asia estimate that there may be 350,000 children with autism in Pakistan...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2022
Status: Completed
Advisor
Tahira Lashari [DoC]
Committee Members
Arham Muslim [DoC] Farzana Jabeen [DoC]
Students
Iqra Farid [MSITL-2K20]

72 .
Generating Pseudo Labels for Rice Crop Classification in Punjab Region: A Two-Stage Approach:

Remote sensing (RS) datasets have gained popularity due to their impact on addressing global issues such as food security and climate change. Machine learning (ML) scientists are trying to combine earth observation (EO) data with ML to extract useful information that can help policymakers to design their policies and operations to address the aforementioned global issue. However, RS datasets pose...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Muhammad Moazam Fraz [DoC]
Committee Members
Rai Sajjad [HU] Zuhair Zafar [DoC] Fahad Ahmed Satti [DoC]
Students
Ramesha Murtaza [MSAI-2K21]

73 .
Empowering Farmers through Data: Pak Kasaan, A Comprehensive Platform for Crop Management and Advance Analysis:

In the society in which we live, there are numerous social issues that we face today. One of the most pressing issues is the farming system in Pakistan. Farmers encounter significant challenges in managing records of their crops due to the persistence of outdated record-keeping techniques and analytics tools. These shortcomings prevent them from effectively predicting crop growth patterns and ana...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Muhammad Moazam Fraz [DoC]
Committee Members
Zuhair Zafar [DoC] Bilal Ali [DoC] Syed Imran Ali [DoC]
Students
Hamza Iftikhar [MSCS-2K21]

74 .
Clinically Significant Prostate Cancer (csPCa) segmentation/Classification using deep learning on multi-parametric Magnetic Resonance (MR) Images:

Prostate cancer is a form of cancer that develops in the prostate gland and is found in males. In the diagnostic procedure of prostate cancer (PCa), Multi-Parametric Magnetic Resonance Imaging (mpMRI) is recommended to be used. The mpMRI is interpreted by a Radiologists before the biopsy to help in the selection of patients having a risk of clinically significant PCa. Radiologists use the Prostat...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Rafia Mumtaz [DoC]
Committee Members
Muhammad Daud Abdullah Asif [DoC] Mehwish Kiran [EE]
Students
Inshal Saleem [MSDS-2K20]

75 .
Exploring the Impact of DST and Animations on Students Science Skills:

Digital Story telling (DST) is an innovative technique for teaching Science ideas to kids. In this MS Thesis, we shall explore the impact of DST and Students learning and engagement.


Project Level: PG
Project Type: Thesis Knowledge Area: Human-Computer Interaction
Year: 2022
Status: Active
Advisor
Sohail Iqbal [DoC]
Committee Members
Arham Muslim [DoC] Sara Tariq [ECM] Aimal Rextin [DoC]
Students
Rukhma Aijaz [MSITL-2K20]

76 .
Real-Time VoIP Traffic classification using Deep Learning:

Nowadays, the vast majority of traffic is end-to-end encrypted. Therefore, we cannot rely on classical methods. The recent advances in Deep Learning and its ability to recognize patterns and anomalies provide us methods to classify Internet traffic with greater accuracy. In this research, we aim to classify VoIP which constitutes most of the traffic passing through the IP core network. Also, for ...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2022
Status: Active
Advisor
Rabia Irfan [DoC]
Committee Members
Madiha Khalid [DoC] Hafsa Iqbal [EE] Sana Qadir [DoC]
Students
Fahad Naeem [MSCS-2K20]

77 .
A Comparison Study of Android Browsers Forensics for Data Remnants :

Web browsers are ubiquitous in our daily lives. The activities on browsers range widely, such as opening websites, and blogs, watching videos, checking email downloading documents, uploading data to the cloud, and much more. Most cyber activities are performed on web browsers which may lead to cyber attacks as well. Therefore there is important to have an adequate forensics investigation methodo...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Assurance and Security
Year: 2022
Status: Active
Advisor
Mehdi Hussain [DoC]
Committee Members
Sana Qadir [DoC] Hasan Tahir [DoC]
Students
Umair Khan [MSIS-2K20]

78 .
Advanced Threat Pattern Recognition and Visualization in Cybersecurity using Knowledge Graphs and Natural Language Processing:

The increasing complexity and frequency of cyber threats necessitate innovative approaches for effective detection, analysis, and response. Traditional cybersecurity methods often fall short in addressing the dynamic and interconnected nature of modern cyber-attacks. This research presents a novel methodology that leverages Natural Language Processing (NLP) and Knowledge Graphs to enhance the ide...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2022
Status: Active
Advisor
Bilal Ali [DoC]
Committee Members
Syed Imran Ali [DoC] Hasan Ali Khattak [DoC] Shah Khalid [DoC]
Students
Muhammad Qaisar [MSCS-2K21]

79 .
Formal Verification of the Health Code System for Quarantine Management: A Case Study in China:

A Contagious disease known as Novel Coronavirus (COVID-19) was first identified in Wuhan, China. Later, it spread across the world, leading to a global pandemic. It affected millions of people by causing some significant social and economic disruption. In response to the pandemic, many countries have implemented lockdowns, social distancing, and enforced wearing face masks to control the spread. ...


Project Level: PG
Project Type: Thesis Knowledge Area: Computational Science
Year: 2022
Status: Active
Advisor
Aimal Rextin [DoC]
Committee Members
Sohail Iqbal [DoC] Iram Tariq Bhatti [DoC]
Students
Shahid Ali Khan [MSCS-2K20]

80 .
Coverage enhancement using heterogeneous links for smart ocean:

This study explores how cognitive radios can be used to leverage heterogeneous networks and enhance communication coverage in the maritime industry. Because of things like poor infrastructure, distance from shore stations, weather, and expensive deployment costs, maritime operations frequently struggle to establish consistent, long-range communication. The objective is to increase the communicati...


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2022
Status: Completed
Advisor
Huma Ghafoor [EE]
Committee Members
Syed Ali Hassan [EE] Mohaira Ahmad [EE]
Students
Waqas Mustafa [MSIT-2K20]

81 .
Intrusion Detection System using Machine Learning model for IoT using novel Dataset:

IoT is pervasive because of interconnected miniaturized devices. IoT devices are vulnerable and risky for user privacy which is an utmost important thing to be kept secured from intruders. In this thesis, we intend to propose an Intrusion Detection System to monitor the malicious activities over the network for the IoT devices and respond to them efficiently.


Project Level: PG
Project Type: Thesis Knowledge Area: Networking and Communications
Year: 2022
Status: Completed
Advisor
Muhammad Zeeshan [DoC]
Committee Members
Hasan Tahir [DoC] Qaiser Riaz [DoC]
Students
Bilal Zafar [MSIT-2K21]

82 .
Determining the Impact of Events on Pakistan Stock Prices and their Prediction using Urdu News Articles:

Investing in stocks is a risky business. Predicting the movement of the stock market is very
important as it helps investors decide which stocks will be more profitable and which stocks to avoid. However, a model that can achieve this task accurately is still a goal yet to be
accomplished. Each country’s stock market is different in that the factors that influence it, such as certain economic f...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Seemab Latif [DoC]
Committee Members
Rabia Irfan [DoC] Taufique ur Rahman [DoC]
Students
Nikhar Azhar [MSDS-2K20]

83 .
A Novel Job Recommendation System using Natural Language Processing:

This project will develop a job recommendation system that will save time for job
recruiters by taking resumes from candidates. Then the system will analyze and rank
candidates for each job posting using NLP techniques.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Rabia Irfan [DoC] Seemab Latif [DoC]
Students
Hussnain Ahmed Saqib [MSDS-2K20]

84 .
A Novel Job Recommendation System using Natural Language Processing:

This project will develop a job recommendation system that will save time for job
recruiters by taking resumes from candidates. Then the system will analyze and rank
candidates for each job posting using NLP techniques.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Rabia Irfan [DoC] Seemab Latif [DoC]
Students
Hussnain Ahmed Saqib [MSDS-2K20]

85 .
Anticipating the Stock Market Trend using Natural Language Processing Techniques:

In academic and financial circles, understanding the rhythm of financial activities and anticipating their evolution and changes are research hotspots. Predicting the development patterns of financial data is exceedingly challenging due to the fact that it contains complicated, partial, and ambiguous information. Stock market trend analysis is essential because an individual who moves with the tr...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2022
Status: Suspended
Advisor
Seemab Latif [DoC]
Committee Members
Rabia Irfan [DoC] Maajid Maqbool [DoC]
Students
Sana Sajid [MSCS-2K20]

86 .
Detection of Lead Contamination in Surface Water using Remote Sensing and Computer Vision:

Water is essence of life. The use of fertilizers and industrial waste from factories is contaminating drinking water because of waste dumping in rivers, lakes and underground. These factors along with increasing urbanization and population, with no proper control of waste management are contaminating our drinking water. The Lead is a toxic metal which causes severe damages to health. In fact, Lea...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Rafia Mumtaz [DoC]
Committee Members
Tahira Lashari [DoC] Muhammad Daud Abdullah Asif [DoC]
Students
Usama Azim Kundi [MSDS-2K20]

87 .
Early Detection of Cotton Disease using UAV and Sentinel-2 Imagery:

Cotton cultivation is pivotal to Pakistan's economy, contributing significantly to its GDP and accounting for a substantial portion of its export earnings. However, the country currently faces a steep decline in cotton production due to challenges such as reduced sowing area, adverse weather conditions, and pest attacks. This underscores the urgent need for enhanced agricultural data to support e...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Zuhair Zafar [DoC]
Committee Members
Muhammad Moazam Fraz [DoC] Syed Imran Ali [DoC] Fahad Ahmed Satti [DoC]
Students
Noor Us Sabah [MSDS-2K20]

88 .
Multi-task learning for legal judgement prediction :

Humans need to make certain predictions in different sectors of their lives. Similar is the field of law and judiciary. The analysis and implementation of the law is majorly dependent on the legal texts, which requires critical analysis of violated laws and related articles to formulate a final judgement. However, the extraction of relevant data from the legal documents is time-consuming and tire...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Seemab Latif [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Momina Moetesum [DoC]
Students
Rabia Hanif [MSCS-2K20]

89 .
Co-occuring disfluencies in Stuttered Speech: Detection and Classification via Deep Learning Framework:

In this era of technological advancement and unprecedented change where the rate of innovations and discoveries are occurring at quite a pace, whilst, in the field of psychology, assessments are still done manually. Therefore, we believe we can take a step forward to automatize assessments in the domain of stuttering speech disorder. The first step toward automation refers to the classification o...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Active
Advisor
Seemab Latif [DoC]
Committee Members
Rabia Irfan [DoC] Momina Moetesum [DoC]
Students
Huma Ameer [MSDS-2K20]

90 .
Impact of Web 2.0 tools on students learning curve, and self-regulatory behaviour in Pakistani Classrooms.:

Technology has played a fundamental role in our life particularly integration of technology in the field of education has brought drastic changes. Massive amount of information such as e-books, audio and video learning aid are available at fingertip through internet. Literature has revealed that interactivity, involvement in learning and student’s engagement is increased with the usage of modern ...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2022
Status: Completed
Advisor
Tahira Lashari [DoC]
Committee Members
Sara Tariq [ECM] Farzana Jabeen [DoC]
Students
Maheen Zahra Javed [MSITL-2K20]

91 .
Invented Spellings & Vocabulary: The Effects of Direct, In-direct and Supplementary Corrective Feedback on Elementary EFL Learners:

Children transfer phonological awareness across languages, even though the reading and writing systems of their native (L1) and foreign (L2) languages might be completely different. One of the primary processes that English as a foreign language (EFL) learners attempt is invented spelling. Invented spelling is the result of a student’s attempt to spell a word when the correct spelling is unknown....


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2022
Status: Completed
Advisor
Arham Muslim [DoC]
Committee Members
Sara Tariq [ECM] Tahira Lashari [DoC] Sohail Iqbal [DoC]
Students
Azka Rizwan [MSITL-2K20]

92 .
Unconstrained Offline Urdu Handwriting Recognition :

Most research in the field of Urdu text recognition focuses on printed text, whereas handwriting recognition is wide open for new ideas. Urdu Handwriting Recognition is considered a complex task due to complex ligature shapes and writing styles of Urdu language. The majority of research in Urdu handwriting recognition revolves around stroke-based online handwriting recognition in which touch sens...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Moazam Fraz [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
Nauman Riaz [MSCS-2K20]

93 .
Legal Judgment Prediction and Explanation Extraction:

Various attempts have been made in recent years to predict judicial decisions using various machine learning models. Pakistani courts have been battling serious litigation backlogs and court congestion. The goal of this research is to make unbiased judgments in order to facilitate the legal practitioners and investigate how Machine Learning and Deep Learning techniques can be used to analyze text...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Rabia Irfan [DoC] Seemab Latif [DoC]
Students
Arooba Maqsood [MSCS-2K20]

94 .
Integration of Assistive Technology in Existing Syllabus for Kids with Special Needs:

Special education, like mainstream education, is equally as important for an inclusive
and progressive society where no student is left behind. However, due to lack of
research and resource allocation to special education students with special needs do
not have access to the same opportunities as compared to a mainstream student. The
reason for this is lack of progression in the existing syll...


Project Level: PG
Project Type: Thesis Knowledge Area: Social Issues and Professional Practice
Year: 2021
Status: Active
Advisor
Tahira Lashari [DoC]
Committee Members
Arham Muslim [DoC] Farzana Jabeen [DoC]
Students
MAH RUKH ANWAR [MSITL-2K20]

95 .
Analyzing the Severity level of Asthma (SLA) using Artificial Intelligence:

Asthma is a chronic inflammatory lung disease which is characterized by swelling and narrowing of airways. Respiratory sounds are important indicators of respiratory health and respiratory disorders. The sound emitted when a person breathes is directly related to air movement, changes within lung tissue and the position of secretions within the lung. Recent research has proposed intelligent syste...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Committee Members
Muhammad Daud Abdullah Asif [DoC] Naema Asif [DoC]
Students
Khadija Amjad Sipra [MSCS-2K20]

96 .
Hyper-spectral Document Image Segmentation:

Separating overlapping text and non-text from images is one of the challenging tasks in
document analysis and segmentation. It was previously difficult to separate text and
non-text due to a lack of information available in existing datasets consisting of
RGB Images. A hyper-spectral image depicts pixel information into a number of channels than can overcome the constraint of limited pixel inf...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Shahzad [DoC]
Students
Hasan Irtaza Mirza [MSCS-8]

97 .
Relation extraction in Legal Judgements through Neural Tensor Network :

One of the most useful applications of NLP technology is information extraction from unstructured texts i.e., legal documents, contracts, financial documents, healthcare records, etc. that enable automatic data query to derive new insights.
Extracting information defined as entities and finding the relationship between them is a challenging task in semi-structured documents. Our goal is to build...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Rabia Irfan [DoC] Seemab Latif [DoC]
Students
RIDA ALI [MSIT-19]

98 .
Urdu Handwriting Generation using Generative Adversarial Networks (GANs):

Handwriting Recognition systems performance has improved significantly but is still limited by the amount of available training data. Since gathering data is a challenging and costly task, there is a need to increase the dataset by applying different techniques. One possible solution is to make a model that can generate similar yet different samples from the existing data samples. Generative Adve...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Ali Tahir [DoC] Muhammad Imran Malik [DoC]
Students
MARIUM SHARIF [MSEE-11]

99 .
Multi-lingual Traffic Signboard detection and Recognition in Natural Scene Images:

Self-driving vehicles can establish their driving tasks i.e. path planning, navigation, and motion control by understanding the road traffic signboards. Though, convolutional neural networks have demonstrated better applicability in scene-text detection and recognition. However, real-time scene text detection and understanding of traffic signboards is a challenging task. This study focuses on mul...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Shahzad [DoC] Muhammad Imran Malik [DoC]
Students
MUHAMMAD ATIF BUTT [MSCS-9]

100 .
Improving the performance of Pakistan's judicial system and it's ranking using data analytics:

The World Justice Project (WJP) is an independent, multidisciplinary organization, working to advance the rule of law worldwide. It covers 128 countries and jurisdictions. It relies on national surveys and responses from legal practitioners and experts. The performance of a country is measured on the basis of 8 categories, which are further divided into 44 indicators. The performance of Pakistan ...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2020
Status: Completed
Advisor
Rabia Irfan [DoC]
Committee Members
Faisal Shafait [DoC] Seemab Latif [DoC] Adnan Ul-Hasan [ECM]
Students
FAISAL MEHMOOD [MSCS-8]

101 .
Price & Load Forecasting in a Deregulated Energy Market using a Hybrid Deep Neural Network Approach:

In many countries including Pakistan, the electric power industry has been undergoing
deregulation through the introduction of competition. Accurate System Marginal Price
and Load forecasts play an important role in an economic power dispatch, system
reliability and planning.  In a competitive wholesale Energy market, individual
generating stations submit their pricing bids on a day-ahead bas...


Project Level: PG
Project Type: Thesis Knowledge Area: Algorithms and Complexity
Year: 2020
Status: Completed
Advisor
Muhammad Shahzad [EE]
Committee Members
Faisal Shafait [DoC] Muhammad Shahzad [DoC] Wajahat Hussain [EE]
Students
MUHAMMAD FURQAN AZAM [MSEE-9]

102 .
Attention based bidirectional GRU hybrid model for inappropriate content detection in Urdu language:

Broadcast media is monitored by the organizations who wish to keep track of the items being aired such as Pakistan Electronic Media Regulatory Authority (PEMRA). Of late, the broadcasting content is increasingly available online in the form of text and videos as well. Timely identification of unsuitable or banned content broadcasts can speed up the process of taking legal action for the violation...


Project Level: PG
Project Type: Thesis Knowledge Area: Information Management
Year: 2020
Status: Completed
Advisor
Rabia Irfan [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Ali Tahir [DoC] Muneer Ahmad [DoC]
Students
EZZAH SHOUKAT [MSIT-19]

103 .
Localisation of Abnormalities in EEG signal:

Automatic analysis of EEGs provides a clinical decision support tool that can reduce time to diagnosis and assist clinicians in real-time monitoring applications. In this study, a high-performance automated EEG analysis system based on principles of deep learning is proposed.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Shahzad [DoC] Muhammad Ali Tahir [DoC]
Students
TAYYABA FAISAL [MSCS-8]

104 .
Automated Signature Analysis & Verification:

Handwritten signature analysis is an active area of research where the current project would aim at solving the problem of extraction and verification of signatures from multifarious document images.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Shahzad [DoC] Muhammad Ali Tahir [DoC]
Students
NOOR UL AIN IBRAHIM [MSIT-19]

105 .
Automated Anonymization of Court Room Records:

Thousands of cases are registered every year in High Courts and the Supreme Court of Pakistan and the judgments of these cases are available on their respective websites in the form of PDF documents. Since these documents are easily accessible containing personal information of the parties involved such as petitioner and respondent names, addresses and in some cases their CNIC numbers, anyone can...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Seemab Latif [DoC] Rabia Irfan [DoC]
Students
MARIUM DAUD [MSCS-8]

106 .
Smart annotation approaches for medical imaging:

Labeling of medical data requires investment of a large amount of time and monetary resources. This project will explore smart annotation techniques for medical imaging applications such as digital pathology. The objective is to make it easy to generate large amounts of labelled data for supervised or weakly supervised learning.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Wajahat Hussain [EE]
Committee Members
Faisal Shafait [DoC] Khawar Khurshid [EE] Muhammad Imran Abeel [EE]
Students
KOMAL MARIAM [MSEE-9]

107 .
Text Summarization from Judicial Records using Deep Neural Machines:

The judiciary is the branch of the government whose task is the administration of justice. The courts are generating a large amount of data as legal proceedings. The legal documents are in the form of cases and their judgments. A judgment is a long, and detailed document. In order to prepare for a case, a lawyer has to read through hundreds of legal documents to find out the relevant judgments. I...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Seemab Latif [DoC] Rabia Irfan [DoC]
Students
AYESHA SARWAR [MSCS-8]

108 .
CBR-based Similar Case Retrieval from Judicial Records:

A system that can retrieve similar cases will not only lessens human effort but also reduce the amount of time it would take to retrieve similar cases.
The techniques in Case Based Reasoning (CBR) can be used to index, find, retrieve, and rank the cases that are most similar to a newly registered case. The dataset used will be the judgments from the courts of Pakistan.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Seemab Latif [DoC] Rabia Irfan [DoC]
Students
MEHREEN GUL [MSCS-8]

109 .
Information Extraction from Court Room Records:

Information extraction is one of the most difficult tasks when it comes to retrieving information especially from semi-structured documents. But on the other side, it is most useful when information is required for indexing and analyzing the data. The judgments found in the different courts of Pakistan do not follow a standard format overall rather many different types of formats have been found....


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Seemab Latif [DoC] Rabia Irfan [DoC]
Students
NIDA AHMED [MSCS-8]

110 .
Liveness Detection:

Know Your Customer (KYC) is a vast field potentially sought after every business in the category of B2C. Knowing the customers induces confidence in dealing with the customer and ensures minimal fraud. Although, with current situations of global pandemic and general technological movement, both companies and customers seek an easy way out of verification. This project will potentially create a wh...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2019
Status: Completed
Advisor
Safdar Abbas Khan [DoC]
Committee Members
Iftikhar Ahmad Rana [EE] Muhammad Khuram Shahzad [DoC] Ibrar Hussain [BS]
Students
TAUSEEF MEMON [MSCS-8]

111 .
AI based Dengue Fever Prediction using Deep Learning:

Dengue epidemic is a major public threat in Pakistan since 2005, following millions of people at risk. To account for the human suffering caused by the epidemics of dengue, the project aims to develop a system that provides a cost-effective and rapid solution for diagnostic screening of dengue. Artificial Intelligence powered system accompanied by a medical chatbot, providing an easy-to-interact ...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Shahzad [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
MAHNOOR HANEEF [MSEE-9]

112 .
Crop Monitoring Via Remote Sensing:

The increasing world population is generating higher food demand that needs effective cultivation methodologies to meet them, especially for the developing countries that have a higher dependence on the agricultural sector. Crop type classification is part of crop monitoring which can help to plan crops effectively and meet the demandsupply chain. Our study had mainly two objectives, acquisition ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Qaiser Riaz [DoC] Rafia Mumtaz [DoC]
Students
ZUBAIR IQBAL [MSCS-7]

113 .
Applications of Low Dimensional Manifold Method in MRI and Depth Image Reconstruction:

Recently (Osher et al. 2017) proposed a low dimensional manifold model (LDMM) for image inpainting and denoising. The basic assumption of LDMM is that the image patches sample a manifold whose intrinsic dimensions are much lower than the high dimensional ambient space. Based on this assumption, the image is recovered by keeping the dimension of the patch-manifold as small as possible. LDMM has b...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Omar Arif [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Moazam Fraz [DoC] Muhammad Shahzad [DoC]
Students
SAIM ABDULLAH [MSCS-8]

114 .
Detection of Student behavior in Classroom:

This research aims for scrutinization of students in a classroom environment and can be used as an alternate for monitoring an attention of students in real-time. Detection of attentiveness and not attentiveness of students studying in school, collages and university could help to identify the weaknesses and strengths of any educational institute. Human factor is the main and the most critical pa...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Shahzad [DoC] Muhammad Imran Malik [DoC]
Students
NAQASH GERARD [MSITL-6]

115 .
Large Scale Fine-Grained Visual Recognition:

Large scale fine-grained visual recognition is a very challenging area as models must find discriminative features between sub-categories of the objects. The use cases include identifying animal breeds, car models or hair colors in stores. The current best methods include deep learning-based methods which are complex, resource-intensive and slow to train. The aim of this research is to use teach...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Imran Malik [DoC] Adnan Ul-Hasan [ECM]
Students
OMER USMAN UPPAL [MSCS-7]

116 .
Vehicular Traffic Flow Parameter Estimation Using Deep Neural Networks:

To overcome the challenges regarding the fixed place camera installation we introduce a drone-based real-time traffic flow parameter estimation. With the recent convenience of UAV (Unmanned aerial vehicles) videos begin a new smart transportation application. We Captured the live vehicles traffic data using DJI Phantom 4 Pro drone from 8 AM - 6 PM. We manually annotated the vehicle instances of a...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Moazam Fraz [DoC] Muhammad Imran Malik [DoC]
Students
MUHAMMAD RAEES [MSCS-7]

117 .
Deep Learning for Forensic Examination of Handwritten Text:

Forensic Handwriting Examiners (FHEs) often have the scenarios where they are provided with a piece of text handwritten by an author in a different style than those texts which are present in the dataset and were written by the same author. This is a usual situation when the same person, for example, writes threat letters to more than one persons and tries to change her/his handwriting style ever...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Withdraw
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Shahzad [DoC] Muhammad Ali Tahir [DoC]
Students
MUHAMMAD MOHSIN [MSCS-8]

118 .
Abstractive Text Summarization of Judicial Cases in Supreme Court of Pakistan:

Due to the huge amount of legal information availability on the internet, as well as other sources, it is important for the research community to do more extensive research on the area of legal text processing, which can help us make sense out of the vast amount of available data. This information growth has compelled the requirement to develop systems that can help legal professionals as well as...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC] Muhammad Shahzad [DoC]
Students
MUNEEB AHMED ANWAR [MSIT-18]

119 .
One-Shot Vehicle Re-Identification:

Vehicle reidentification is an important part of intelligent traffic monitoring systems, whose application doesn’t just limit to vehicle monitoring or surveillance. Having an efficient vehicle reidentification procedure allows a system to accurately and timely detect/track a vehicle, which can play an important part in doing forensic analysis as well.
The procedure that will be used is Siamese N...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Moazam Fraz [DoC] Muhammad Imran Malik [DoC]
Students
HASSAN FAROOQ [MSCS-7]

120 .
Adversarial Attacks on Deep Neural Networks:

Deep neural networks are increasingly being used for classification tasks. Image classfication is the area using DNN extensively. These classification models are deployed in real time and laboratory environments. In some applications these networks are vital to the security of access points using these networks. In order to check the robustness of the networks, adversarial attacks are being carri...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Shahzad [EE] Muhammad Shahzad [DoC]
Students
SALAH UD DIN [MSEE-9]

121 .
Crop classification though low altitude remote sensing platforms:

Remote sensing has been found to be a valuable tool in evaluating, monitoring and management of land, water and crop resources. Satellite imagery and aerial imagery have wide applications in the field of agriculture, monitoring snow cover trends, wild fire trends, water level rising and forestry. In agriculture, crop health monitoring, yield estimation, classification of crops based on land cover...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Shahzad [DoC] Safdar Abbas Khan [DoC]
Students
NAVEED IQBAL [MSIT-18]

122 .
Deep Learning based Supervised Classification of Water Bodies from High-resolution Multispectral Sentinel-2 Imagery:

The rapid growth of technology in the fields of remote sensing, image acquisition and data storage has led to an enormous increase in volume of available high-resolution satellite image data. One of the most challenging tasks faced by scientists these days, is the efficient and precise use of satellite images for earth observation. Due to its high resolution and multispectral characteristics, sat...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Imran Malik [DoC] Adnan Ul-Hasan [ECM]
Students
RAFIA MALIK [MSCS-7]

123 .
How do people look at crowds? A psychophysics perspective :

Crowds of people offer multitudes of stimuli for attracting gaze and attention. It is a fact that during normal social interactions, faces are the most important stimuli. We are interested in exploring if this statement holds in conflation with crowd density (the number of people per square area). To this end, we would like to understand this relationship between human gaze and varying crowd dens...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Omar Arif [DoC]
Committee Members
Faisal Shafait [DoC] Anis ur Rahman [DoC] Muhammad Muneeb Ullah [DoC]
Students
SOBAS MEHBOOB [MSCS-7]

124 .
Predictive visual saliency model for crowd videos :

What do people look at first, instantaneously and inadvertently? The answer would be: They look at what is salient. Visual Saliency is an ongoing area of research interest to figure out what captures bottom-up attention. This is an important question because visual saliency provides the link between the perception of external stimuli and human cognition. Understanding Visual Saliency means to und...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Omar Arif [DoC]
Committee Members
Faisal Shafait [DoC] Anis ur Rahman [DoC] Muhammad Muneeb Ullah [DoC]
Students
MEMOONA TAHIRA [MSCS-7]

125 .
Pansharpening of Multispectral images using dual attention based two stream network:

With the advent of technology there are large number of earths observing satellites having sensors, delivering different type of images that can provide a varying useful information about different surfaces of earth and those areas that are not reachable by human. Most popular of these images are panchromatic (PAN) image having the geometric details and multispectral (MS) image that contains refl...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Anis ur Rahman [DoC] Muhammad Muneeb Ullah [DoC]
Students
SYEDA ROSHANA ALI NAQVI [MSCS-7]

126 .
Simulation Modelling and Forecasting of Dengue Spread using Agent-based Modelling:

Dengue fever is a viral infectious disease that is affecting over 110 countries in the world. It has become an international public health concern and about 50 million people get infected among which 10000-20000 die each year. Dengue is principally transmitted by either of two types of infected female mosquitoes named Aedes aegypti and Aedes albopictus. Factors that influence dengue includes clim...


Project Level: PG
Project Type: Thesis Knowledge Area: Software Engineering
Year: 2018
Status: Completed
Advisor
Imran Mahmood [DoC]
Committee Members
Faisal Shafait [DoC] Muazzam A Khan Khattak [DoC] Sharifullah Khan [DoC]
Students
Mishal Jahan [MSIT-16]

127 .
Optical Music Recognition using Deep Learning:

Optical Music Recognition is a field of research that investigates how to computationally
decode music notation from images. Despite the efforts made so far, there are hardly any end to end complete solutions to the problem which is dealing with a comprehensive set of notation symbols. Using a neural model that combines the capabilities of CNN, which work on the input image, and RNN, which deal ...


Project Level: PG
Project Type: Thesis Knowledge Area: Computational Science
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Shahzad [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
MUHAMMAD FAROOQ [MSCS-6]

128 .
Smart Surveillance through Periocular Biometrics:

Face recognition has paved its way to success in the recent years and has been intelligently merged with modern technologies. Nowadays, face recognition techniques are extensively used by law enforcement agencies worldwide. In our country, there is a significant need of a system which forms an integrated unit for security surveillance by identifying and recognizing persons through their facial ch...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Muhammad Ali Tahir [DoC] Muhammad Shahzad [DoC]
Students
MUHAMMAD EHSAN IRSHAD [MSCS-6]

129 .
Vehicle Detection in Aerial Imagery:

Aerial surveillance is getting more attention with the increasing use of small drones for different social and military tasks, as a result more aerial data is being produced. Various object and pattern recognition tasks require this data to process, analyze and investigate for effective decision making. Vehicles are most prominent and important objects when observed from an aerial view and identi...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
MUHAMMAD HAROON [MSCS-6]

130 .
An intelligent context-aware recommendation system for real-estate:

Data science is being extensively used to recommend suitable products to end users and consumers. This thesis will focus on understanding a user requirements based on his browsing history as well as interaction with the website through a chatbot and recommend the products that the user will be interested in. The primary use case for this work will be in the domain of real-estate and the system wi...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Shahzad [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
Faiza Rehman [MSIT-16]

131 .
Urdu Text to Speech System for Navigation App:

Due to increase in taxi hailing service (Uber & Careem), a demand for Urdu text to speech system was increasing. This system would be used in a Pakistani navigation app which would facilitate the drivers(captains) in finding a way without keeping an eye on the mobile. The goal is to provide Pakistani people the language in which they are most comfortable i.e. Urdu. In Pakistan, most of the driver...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Ali Tahir [DoC]
Committee Members
Faisal Shafait [DoC] Qaiser Riaz [DoC] Safdar Abbas Khan [DoC]
Students
Muhammad Asfand [MSCS-5]

132 .
Nuclei segmentation using deep learning:

Cancer detection from histopathological images requires manual examination by trained professionals which requires a lot of effort and time. This process is subjective hence more error prone. But with the easy digitization and storage of tissue slide images the prospect of an automatic analysis system has grown. Benefits of such a system are wide reaching especially in developing countries wher...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2018
Status: Active
Advisor
Hassan Aqeel [EE]
Committee Members
Faisal Shafait [DoC] Khawar Khurshid [EE] Ahmad Salman [EE]
Students
Muhammad Uzair Khan [MSCS-5]

133 .
Machine Learning Based QBE Word Spotting of Urdu Text:

With increased digitization of documents over the past decades, the task of
word spotting has acquired much significance in the field of document analysis
and recognition. Deep learning has revolutionized many fields and promises
to make similar inroads in this field and improve performance for various
document analysis tasks. This research presents a systems for the task of
word spotting of...


Project Level: PG
Project Type: Thesis Knowledge Area: DSSP
Year: 2018
Status: Completed
Advisor
Muhammad Shahzad [EE]
Committee Members
Faisal Shafait [DoC] Wajahat Hussain [EE] Junaid Qadir [EE]
Students
FAIQ FAIZAN [MSEE-8]

134 .
Automated quantification of cancer pathology slide images obtained via low quality images.:

Histopathologic analysis of digitized slides of cancer images has benefited significantly from recent advances in machine learning. Unfortunately, all existing approaches assume the availability of whole slide imaging (WSI) scanners for slide digitization. WSI scanners are expensive and cannot be afforded by pathology labs in developing countries. This project will investigate the possibility of ...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Hassan Aqeel [EE]
Committee Members
Faisal Shafait [DoC] Khawar Khurshid [EE] Wajahat Hussain [EE]
Students
WAJAHAT NAWAZ [MSEE-8]

135 .
Discriminative splitting of LSTM-RNN deep neural networks for robust speech recognition:

LSTM-RNN are state of the art for acoustic model training. However, training such parameters is susceptible to over-training phenomenon, which reduces the accuracy of the system. To solve this problem, discriminative splitting of parameters can be used, previously applied by the author on feed-forward deep neural networks. Now we will investigate the use of this technique on LSTM-RNN


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Muhammad Ali Tahir [DoC]
Committee Members
Faisal Shafait [DoC] Hassan Aqeel [EE] Ahmad Salman [EE]
Students
Muhammad Irfan [MSCS-5]

136 .
Information Extraction from Tables in Document Images using Deep Learning:

Table structure extraction is a challenging problem due to the diversity of layouts in which tabular information is presented. This problem is further complicated when a printed invoice is captured by a mobile phone camera, since the capture induces perspective and page curl distortions that result in distorting the alignment in table columns. This thesis aims at addressing these issues in a gene...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Shahzad [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
Muhammad Shahzad [MSCS-5]

137 .
Postal Address Parsing using Deep Learning:

Parsing of postal addresses is a standard procedure in postal automation. However, disambiguating between names and position is a challenging problem. Besides, non-standardized addresses are difficult to tackle with traditional approaches. This thesis aims at developing a deep learning based solution to address the challenges in postal address parsing.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC] Muhammad Shahzad [DoC]
Students
NOSHEEN ABID [MSCS-6]

138 .
Table Detection using Attention Based Networks:

This thesis aims at detecting tables in document images using attention-based deep networks. Table detection remains an unsolved problem due to the diverse visual appearance of tables and their complex structures.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC] Muhammad Shahzad [DoC]
Students
SAMAN ARIF [MSCS-6]

139 .
Incremental Learning of Object Detectors using Limited Training Data:

Object detectors in practice find it hard to generalize due to the wide variety of object categories present in real world environments. Incremental learning aims at providing more control to the end users of the object recognition technology so that they can add more object categories to be recognized without the intervention of the machine learning expert. This thesis will focus on indoor objec...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC] Muhammad Shahzad [DoC]
Students
MUHAMMAD ABDULLAH HAFEEZ [MSCS-6]

140 .
Table structure extraction from document images:

The objective of this thesis will be to effectively extract structured information with good accuracy from tables present in the documents images.

As the industries are getting digitized now-a-days, optical character recognition is adding a huge value in the transformation process by extracting text information from document images. Tables contains information points for a large number of item...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC] Muhammad Shahzad [DoC]
Students
FAISAL HUSSAIN SABIR [MSCS-6]

141 .
Automated Vehicle Detection in Aerial Imagery:

Detecting military vehicles and distinguish them out from non-military vehicles is a major challenge in the defence sector. An accurate and a faster detection of military vehicle could help to identify enemy’s move and early precautionary measures. In recent years, several deep learning based techniques have been proposed for object detection purposes. However, these were developed using such dat...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Committee Members
Faisal Shafait [DoC] Adnan Ul-Hasan [ECM] Muhammad Imran Malik [DoC]
Students
FARRUKH KAMRAN [MSCS-6]

142 .
Runway detection and localization in aerial images for UAV landing using deep learning:

Landing is the most difficult phase of flight for a drone. Due to lack of efficient systems, there has been numerous accidents resulting in damaged hardware. For safe landing a drone, accurate recognition of landing site is required. Different techniques for automatic landing have been proposed from simple radar based, GPS systems to complex vision based systems. Vision based systems have been pr...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Hassan Aqeel [EE] Adnan Ul-Hasan [ECM]
Students
Javeria Akbar [MSCS-5]

143 .
Information extraction from document forms using Deep Learning:

In everyday life a lot of information is stored in forms (documents). Extraction of this information is important for automating the complete document processing pipeline.
This research will focus on the application of deep learning in order to extract information from forms.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Committee Members
Faisal Shafait [DoC] Hassan Aqeel [EE] Adnan Ul-Hasan [ECM]
Students
Khurram Shehzad [MSCS-5]

144 .
Table Detection in Document Images using Deep Learning:

Table detection is a hard problem due to heterogeneous nature of document layouts and table structures. Existing algorithms for table detection focus on engineered methods for solving the problem. This thesis will focus on a data driven approach for spotting tables in documents using deep learning.


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Muhammad Imran Malik [DoC] Hassan Aqeel [EE] Adnan Ul-Hasan [ECM]
Students
Azka Gilani [MSCS-5]

145 .
Urdu Handwriting Recognition using Deep Learning:

Arabic like scripts (e.g., Urdu Nastaleeq) are cursive in nature even in their printed form. Unconstrained handwritten text in such scripts pose a stern challenge for a deep learning based text recognition system as diverse writing styles make training very challenging. Successful training of deep learning algorithms depends heavily on the availability of huge amount of training data. Since neura...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Committee Members
Adnan Ul-Hasan [ECM] Ahmad Salman [EE] Muhammad Imran Malik [DoC]
Students
Muhammad Mubasher Khan [MSCS-5]

146 .
A Framework to Combine Multi-Object Segmentation and Tracking:

We propose to implement a framework in which multi-object tracking and segmentation are combined in one energy function to each task's mutual benefit. The tracking module will enforce higher-order smoothness constraints on the object trajectories and Lagrangian relaxation is used to get an iterative solution method in which these constraints are relaxed to form modified cost network flow problems...


Project Level: PG
Project Type: Thesis Knowledge Area: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Anis ur Rahman [DoC]
Committee Members
Faisal Shafait [DoC] Asad Anwar Butt [DoC] Safdar Abbas Khan [DoC]
Students
Sehr Nadeem [MSCS-5]

1 .
Self-Optimizing Rewards: Leveraging LLMs for Context-Specific Reinforcement Learning:

This project aims to transform reinforcement learning by allowing Large Language Models (LLMs) to create their reward functions based on the specific needs of different tasks. Traditional methods rely on manually designed reward functions, which can be time-consuming and may not adapt well to various tasks. By using LLMs' built-in understanding of tasks, this project seeks to develop adaptive, co...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muhammad Armaghan Shakir [BESE-12]


2 .
X-AI for Automated EEG Interpretation:

The project aims to develop an innovative AI system capable of analyzing electroencephalogram (EEG) data to generate comprehensive and explainable diagnostic reports for neurological disorders.

EEG is a critical diagnostic tool used to monitor brain activity and detect abnormalities associated with various neurological conditions. However, the interpretation of EEG data requires specialized e...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Naseer Bajwa [DoC]
Students
Waleed Ahmed [BESE-12] Zainab Saad [BESE-12]


3 .
Segmentation of Post-Fire Burned Regions in low-resolution satellite imagery:

By using AI, the project aims to accurately delineate burned regions in low-resolution satellite imagery. As a first step, the resolution of open-source satellite imagery will be enhanced using image super-resolution techniques. As a second step, burned image segmentation in the images will be performed using state-of-the-art techniques.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Azka Basit [BSCS-11]


4 .
Biomass Calculation and carbon stock estimation using aerial imagery:

Traditional methods of acquiring biomass is one of the biggest inconveniences of forest inventories since it consumes a huge amount of money and time spent in the field measurement. As an alternative approach, airborne LiDAR (Light Detection and Ranging), has become a powerful tool to characterize forest canopy with accuracy and effectiveness. The LiDAR sensor is deployed on an Unmanned Aerial Ve...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2024
Status: Active
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Huzaifa Jawad [BSCS-11]


5 .
PrepVRse: Enhancing Communication Skills through Virtual Reality and Large Language Model based Feedback System:

PrepVRse is a virtual reality (VR) based product aimed at enhancing communication skills for individuals of all levels using Large Language Models (LLMs) and Computer Vision. By leveraging immersive technology, PrepVRse provides a realistic and engaging environment to develop effective communication abilities. Through interactive simulations, users can practice presentations, refine their speakin...


Project Level: UG
Project Type: FYP
KnowledgeArea: Human-Computer Interaction
Year: 2023
Status: Completed
Advisor
Arham Muslim [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Muhammad Ali Raza Dar [BESE-11] Dawood Mehmood [BESE-11] Tanzeel Ur Rehman [BESE-11]


6 .
Super-Resolution for Early Detection of Forest Health Decline:

With the increased Government of Pakistan measures towards afforestation projects, it is equally important to perform early damage detection of the new plantations in order to ensure healthy development of the trees.Through this project, an automated health assessment of the trees in the BTAP regions will be performed by using high resolution remote sensing data and deep learning topologies.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Hanan Abid [BSCS-10] Salman Arif [BSCS-10]


7 .
Attentiveness Detection in a Metaverse classroom:

The project will aim to develop an attentiveness detection system for an AI based tutor in Metaverse. Through this mechanism, the tutor in the metaverse will be able to assess the student behavior in the class generate an analysis report about it.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Mujtaba Akbar [BSCS-10] Muhammad Waleed Mujahid [BSCS-10] Hamid Muzaffar Khan [BSCS-10]


8 .
AI-based Conversational Bot in Metaverse :

The project will aim to develop an institute in Metaverse (called Meta-Institute) having the facility of a tutor for teaching. The tutor/bot will be able to converse with the students, ask them questions, and give them feedback. The combination of the open-source large language model, LLaMA-2 7B, with optimization techniques QLora and Lora, alongside speech-to-text and text-to-speech models, will...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Raja Haider Ali [BESE-11] Kamlesh Kumar [BSCS-10]


9 .
Automatic CNIC Content Detection using Deep Learning:

The project will aim to develop an application for Urdu CNIC detection using deep learning methods. The project will assist in the security applications to verify the authenticity of the CNIC data and help identify false intrusions instantly.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muhammad Saad Ur Rehman [BSCS-10] Syed Asadullah Kashif [BSCS-10] Muhammad Ali Abbas [BSCS-10]


10 .
Action Transformers for Natural Language Interaction with the Web:

Action Transformers have made the next front line in the AI developments. Currently, the AI models have a major limitation is that they lack the ability to take action in the digital world they operate in. This means that while they can process and analyze vast amounts of data, they cannot actually act upon it.To address this limitation, Action Transformer is designed to enable AI systems not onl...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muneeb Muhammad [BSCS-10] Ali Raza [BSCS-10] Duaa Omer [BSCS-10]


11 .
Reinforcement Learning of Generative Pretrained Transformers for Virtual Agents:

This project will aim at developing an interesting application of Generative Pretrained Transformers (GPT) for virtual agents (chatbots etc.). The major difference between the traditional and latest GPT model lies in the reinforcement learning which involves training the language model using feedback from human evaluators. The same idea will be used to collect the data by asking human annotators ...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Zeeshan Memon [BESE-11] Muhammad Arham [BESE-11]


12 .
Exploring Hardware Software Co-Design for Efficient Implementations of Transformers on FPGAs for edge inference:

In this project, we tackle the challenge of accelerating Vision Transformers on FPGAs through a
comprehensive approach that involves hardware-software co-design, quantization, and
optimization. Our objective is to enhance performance, reduce model size, and optimize power
consumption while leveraging state-of-the-art research. By combining these strategies and
deploying them on selected FPGA ...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Saad Ullah Khan [BEE-12]


13 .
Vision Transformer on Embedded Devices:

Transformers is one of the major cutting edge models these days. The biggest challenge with the transofmrer lies in its computationally expensive training. There is also a lot of latency because the inferencing takes longer because of how large they are. The major idea of this project is to optimize the transformers to create a lite version that can be deployed on the edge devices.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muhammad Hamza Javaid [BEE-12] Talha Israr [BEE-12] Rakhmeen Gul [BEE-12]


14 .
Transformer application on Computer Vision: Advanced Driver Assistance System (ADAS):

This project uses computer vision to introduce a high-performance Advanced Driver Assistance System (ADAS). We propose a novel architecture by merging a CNN-based CLRerNET for lane detection with a Real-Time Detection Transformer (RT-DETR) for object detection, which achieves simultaneous lane segmentation and vehicle detection in real time. RT-DETR utilizes cutting-edge techniques such as a hybr...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2023
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Abdus Sami [BEE-12] Muhammad Ali Afridi [BEE-12] Muhammad Ahmad Usman [BEE-12]


15 .
Forest Damage Detection using Unsupervised Learning:

Since data acts as a fuel for deep learning algorithms, the limitations of dataset availability in Pakistan can become a blocker for the development of a high-accuracy damage detection topology. The blocker can be overcome by exploring the unsupervised learning techniques not confined to a particular disease but to a greater extent of forest damage detection. As an initial step, we shall explore ...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muneeb Elahi Malik [BEE-11] Haleema Ushaq [BEE-11] Muhammad Asim [BEE-11]


16 .
Semi-supervised Abnormality Detection in EEG Signals:

This project will focus on the analysis of EEG signals and classifying the normal EEG from abnormal EEG using AI-powered algorithms. The semi-supervised approach will be used for this purpose


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Sadeed Ahmad [BEE-11] Taimoor Arshad [BESE-10] Muhammad Jamal [BESE-10]


17 .
3D Point Clouds on Embedded Platforms :

Deep Neural Networks are computationally expensive computational machines and require intensive computing resources. An emerging trend in this domain is to run these algorithms on stand-alone machines using FPGAs which have limited computing resources as well as power consumption. Current research aims to further build on this idea and work on its applications.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2022
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muhammad Junaid Ali Asif Raja [BEE-11] Sannan Zia Abbasi [BEE-11] Amur Saqib Pal [BEE-11]


18 .
Localization of Abnormalities in EEG Signals:

Automatic analysis of EEGs provides a clinical decision support tool that can reduce time to diagnosis and assist clinicians in real-time monitoring applications. In this study, a high-performance automated EEG analysis system based on principles of deep learning is proposed which will localize the occurence of abnormalities in EEG signal resulting in the medical practitioners to cut down on the ...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Hassan Aqeel Khan [EE]
Students
Muiz Alvi [BEEE-10] Adil Jowad Qureshi [BEEE-10] Haziq Arbab [BEEE-10]


19 .
Adversarial Attacks on Self Driving Cars :

Deep neural networks (DNNs) are being successfully used in vision-based autonomous driving systems, but are found vulnerable to adversarial attacks where small-magnitude perturbations into the inputs during test time cause dramatic changes to the outputs. A lot of attacks and defense methods have been introduced by different researchers in literaure that revolve around digital world problems. Thi...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad Younis [EE]
Students
Muhammad Umar Javed [BSCS-8] Muhammad Hasnain Naeem [BSCS-8]


20 .
Machine Learning based Smart System for EEG Classification :

With the emergence of smartphones, heavy computers and machinery can be easily replaced in multiple fields. This project will focus on developing an end-to-end system that deploys machine learning with servers at the backend for the classification of normal and abnormal EEG. The system will enable on-time detection of abnormal EEG and assist the medical practitioners in making informed decisions.


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Hassan Aqeel Khan [EE]
Students
Talia Khan Khattak [BSCS-8] Anum Zehra [BSCS-8]


21 .
Visnotate: Prompt Generation of Labelled Data for Medical Imaging:

One of the key bottlenecks preventing researchers from leveraging the true potential of deep learning in medical imaging applications is the non-availability of large datasets. Although data digitization has enhanced the speed of data acquisition, labelling of medical imaging data requires investment of substantial effort by Doctors. Eye gaze annotations have the potential to speed up the data la...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Hassan Aqeel Khan [EE]
Students
Mohammad Hamza [BSCS-8] Affan Zafar [BSCS-8] Musharraf Tameer Islam [BSCS-8]


22 .
Forest Cover Change Detection using 3d Point Clouds on Embedded Platforms:

Deep Neural Networks are computationally expensive computational machines. An emerging trend in this domain is to run these algorithms on stand-alone machines using FPGAs. Current research aims to further build on this idea and work on its applications


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Khuzaeymah Bin Nasir [BEEE-10]


23 .
Deep Learning based Forest Health Analysis:

In the recent years, deforestation has emerged as one of the biggest environmental degradation issue. Governments all over the world are striving to develop monitoring mechanisms to save the forests. Several programmes have been initiated by Pakistani government for forest cultivations, such as billion tree Tsunami Program. This project will focus on the deep learning based forest change detectio...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2021
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Ziayan Javed [BSCS-8] Mian Muhammad Ishaq Khattana [BSCS-8] Saad Amir [BSCS-8]


24 .
MMS: structural design and analysis of pathology images:

3
Interests
MMS: Microscope based Medical imaging scanner:
Medical imaging equipment is very expensive and rarely available in developing countries. We have proposed a low cost, modular, micro-scope based medical imaging scanner.


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2020
Status: Completed
Advisor
Muhammad Imran Abeel [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Talha Mehboob [BEEE-9]


25 .
Brand Coverage in TV Streams:

Brands pay hefty amounts to different channels for their product advertisement. They are interested to know whether the channels are justifying their sponsored material by giving them ample on-screen time and primetime coverage. Therefore, we will develop a web-based brand coverage analytics system to monitor advertisements in multiple TV channels and companies can analyze their sponsored product...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muneeb Aijaz [BESE-8] Radia Zubair [BESE-8]


26 .
MMS: Microscope based Medical imaging scanner:

Medical imaging equipment is very expensive and rarely available in developing countries. We have proposed a low cost, modular, micro-scope based medical imaging scanner.


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2020
Status: Completed
Advisor
Muhammad Imran Abeel [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Muhammad Zeeshan Karamat [BEEE-9] Momin Ahmad Khan [BEEE-9] Muhammad Uzair Khattak [BEEE-9]


27 .
HLS based Implementation of Epilepsy Detection using ANN Architecture on FPGA:

Electroencephalogram (EEG) signals are obtained by the electrical activity of the brain to
determine its normal working and to analyze any sensory loss or unbalanced gestures by neurons. This project aims to present an ANN-based FPGA design to detect epileptic seizures. A lot of work on the detection of epilepsy has already been done for the detection and determination of sleep stages. The main ...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Farheen Asif [BEEE-9] Hasham Mukhtar [BEEE-9] Tauqir Hassan [BEEE-9]


28 .
In-Air Handwritten Sequence Recognition & Verification:

This project aims at creating, recognizing, authenticating, and visualizing documents in air. The focus would be on developing a novel algorithm to convert hand movements in air (captured by a Myo-armband worn by a user) into a sequence of x, y coordinates on a 2D Cartesian plane, and visualize them on a canvas. Existing sensor-based approaches either do not provide visual feedback or represent t...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Haris Riaz [BSCS-7]


29 .
Smart EEG Classifier for abnormality detection:

We aim to develop an annotation tool EEG data annotation using conventional and gaze tracking in order to improve the ML/AL models for better classification and localization of abnormal EEG signals.


Project Level: UG
Project Type: FYP
KnowledgeArea: Electronics
Year: 2020
Status: Completed
Advisor
Muhammad Imran Abeel [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Muhammad Usamah Shahid [BEEE-9] Sadia Asif [BEEE-9] Hamza Azhar [BEEE-9]


30 .
Similar Case Retrieval from Legal Documents:

A system that can retrieve similar cases will not only lessens human effort but also reduce the amount of time it would take to retrieve similar cases. The techniques in Case-Based Reasoning (CBR) can be used to index, find, retrieve, and rank the cases that are most similar to a newly registered case. The dataset used will be the judgments from the courts of Pakistan.


Project Level: UG
Project Type: FYP
KnowledgeArea: Information Management
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Owais Ahmad [BSCS-7] Muhammad Faizan Fareed [BSCS-7]


31 .
Identification of Persons Wearing Masks :

Face recognition techniques had been extensively used for years by law enforcement agencies worldwide. However, due to the current PANDEMIC (CoVid-19), the application of existing face recognition systems has severely reduced--since current approaches fail at recognizing humans wearing masks.
The new dimension, which this project can bring for the researchers, is the identification of people wi...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Osama Mohammed Afzal [BSCS-7] Mohammad Hamza Zakir [BSCS-7]


32 .
Urdu voice based Covid-19 screening helpline:

The telephonic helpline will make thousands of outbound telephonic calls to random people, and will ask them Urdu questions about their health conditions, symptoms and their daily life activities with respect to Covid-19. Based on respondent's answers, the system will guide the user about precautionary measures and how to seek medical help. This system will also collect valuable aggregate statist...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Muhammad Ali Tahir [DoC]
Co-Advisor
Faisal Shafait [DoC] Adnan Ul-Hasan [ECM]
Students
Muhammad Ubaid Ullah [BESE-8] Iqra Shahid [BESE-8] Takreem Masood [BESE-8]


33 .
SmartEEG: An app for collection integration and monitoring of wearable EEG device:

Mobile application is a fast growing segment of global phone market. In this advance world mobile phones are replacing heavy computers in multiple fields. In this project our aim is to develop an application that takes the input from an EEG device via Bluetooth or WiFi and the signals will be shown on mobile screen. Application will contain multiple options for example: specific channels selectio...


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Abeel [EE]
Students
Anas Imran Tasadduq [BESE-8] Syed Anas Kamal [BESE-8] Syeda Ailiya Raza [BESE-8] Muhammad Saad Hussaini [BESE-8]


34 .
Development of Machine Learning Algorithm for Classification of EEG on Mobile Processors:

In this advanced world, mobile phones are replacing heavy computers in multiple
fields. In this project, we aim to develop a machine learning algorithm for the classification of EEG signals. The developed algorithm will be embedded with the mobile phone application that will classify the EEG signal as Normal and Abnormal for the assistance of the examiner. The algorithm will not be computational...


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Abeel [EE]
Students
Ali Abid Chauhdary [BSCS-7] Syed Muhammad Akbar [BSCS-7] Muhammad Haris Owais Ahmed [BSCS-7]


35 .
Development of a Modular EEG Framework for Teaching, Training and Data Collection:

The current state of the art EEG boards is expensive and hard to acquire. We aim to develop a modular open-source EEG hardware with minimum cost. The modular nature will allow us to swap and upgrade modules in the future.


Project Level: UG
Project Type: FYP
KnowledgeArea: Architecture and Organization
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Abeel [EE]
Students
Amna Ahmed Gillani [BEEE-9] Syed Shayan Sohail [BEEE-9] Syed Momin Ali Hashmi [BEEE-9]


36 .
Facial Recognition through Masks for Surveillance:

Recently, everyone has started wearing masks in public due to the ongoing pandemic. Hence a need to recognize people through the mask has arisen for surveillance purposes. Our project focuses on two parts: data collection and developing an algorithm. We will collect data of people with masks on. Then we will compare different algorithms which work best for facial recognition through masks. And fi...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Rabeya Noor [BESE-8] Fatima Binte Hyder [BESE-8] Noor Ul Ain Naqvi [BESE-8]


37 .
Real-time Object Detection for Disaster Management from Aerial Imagery:

Each year, natural calamities and disasters like earthquakes, landslides, flood and typhoon impact broad areas of the world, especially residential areas and man-made structures. In order to decrease the negative impacts of such events, accessibility to real-time and accurate geospatial information of degraded areas is vital at early stages of response. We seek to apply deep learning (DL) techniq...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Siraj Muneer Qazi [BEEE-9] Maryam Sana [BEEE-9]


38 .
Urdu Handwriting Recognition on Mobile Platforms:

Urdu HWR on mobile platforms will be developed during this project. The aim is to deploy DL models on low resource platforms without losing much accuracy. A tool similar to Google Lens for Urdu handwriting will be the likely outcome of this project.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Abdul Rehman [BESE-8] Muhammad Shaharyar [BESE-8] Zain Khalid [BESE-8]


39 .
Waveform Optimization using Neural Network based Real-Time Sensing in 5G Data Links.:

A typical wireless channel has dynamic behavior in terms of noise, multipath fading, and interference. The channel characterization in high capacity data links is a complex task. The physical layers in 4G and 5G avoid this problem with overdesigned parameters in the OFDM access layer without much channel awareness. This conventional approach targets worst-case channel impairments and adjusts key ...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Naveed Ahmed [ECM]
Students
Hadi Askari [BEEE-9] Shaheer Mehmood Bhatti [BEEE-9]


40 .
Pandemic Spread Forecasting:

In this research, we propose to use Artificial Intelligence and Machine Learning to learn the underlying patterns and implicitly model their dynamics in an AI-based forecasting system. We propose to augment Modeling and Simulation with Artificial Intelligence to generate the data for training the AI algorithms. These simulations can be used to design various scenario-based experiments and study d...


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2020
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Saif Ullah [BESE-8] Owais Rehman [BESE-8] Abdul Hafeez Sajid [BESE-8]


41 .
Time-series analysis and prediction of water quality through remote sensing, GIS and IoT:

The periodic time series analysis of different aspects of urban areas is essential owing to the increase in population, stressed resources, and lack of technology-based solutions for effective resource management. In this regard, the temporal analysis of water quality holds paramount importance as it is a key ingredient to sustain life on earth. Water quality depends on many factors like precipit...


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2020
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Abdullah Nasir [BESE-8] Hassan Kumail Ali [BESE-8] Hafsa Zubair [BESE-8]


42 .
Enhanced water quality monitoring and estimation by exploiting multi-modal approach :

With the advent of new technologies such as the Internet of Things (IoT), the water quality can be measured and reported in real-time. However, the limitation of this approach is that it provides point data which is insufficient to represent the entire water body quality unless the water samples are collected from a large number of points and for long durations. The collection of data from multip...


Project Level: UG
Project Type: FYP
KnowledgeArea: Software Engineering
Year: 2020
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Co-Advisor
Faisal Shafait [DoC] Muhammad Shahzad [DoC]
Students
Taimoor Khan Mahsud [BESE-8] Aamir Farooq Khan [BESE-8] Muhammad Usama [BESE-8]


43 .
Line scan camera input processing with LSTM / CNN-LSTM architectures:

In industry often line-scan cameras are used, which acquire just a single pixel-line (or more in some cases). Most often they are placed on top of a conveyor belt. These cameras hence produce an image with a certain width but indefinite height (over time).
The purpose of this research project is to find potential ways to replace computationally expensive CNNs with time sequence models like LSTM...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Abdul Wahab [BSCS-6] Abdullah Rafaqat [BSCS-6] Muhammad Mubashirullah Durrani [BSCS-6]


44 .
Congestion Control in TCP/IP protocol using Deep Learning:

Congestion control in TCP/IP is an important feature to provide smooth Internet Services across varying bandwidth connections. Machine learning techniques have been proposed to effectively manage predictions of congestion before a congestion actually happens. This project will involve deep learning for accurate prediction of congestion. This will help in reducing latency as well as enhance the th...


Project Level: UG
Project Type: FYP
KnowledgeArea: Networking and Communications
Year: 2019
Status: Completed
Advisor
Arsalan Ahmad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Chaudary Muhammad Huzaifah [BSCS-6] Shahmeer Ahmad Khan [BSCS-6] Rayyan Ghani [BSCS-6]


45 .
Unsupervised Forest Segmentation and Classification using Deep Learning:

Unsupervised Forest Segmentation and Classification using Deep Learning


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Nouman Ahmed [BESE-7]


46 .
High Resolution Earth Geo-Observatory System for Sentinel-2 Imagery Using Deep Learning (HR-MARS):

High Resolution Earth Geoobservatory System for Sentinel-2 Imagery Using Deep Learning


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Muhammad Roshan Mughees [BSCS-6] Awais Latif [BSCS-6] Abdul Razzaque Jawad [BSCS-6]


47 .
Forest Change Detection Using Remote Sensing Data:

Forests are the lungs of our planet and their existence is vital to our survival on this planet. However, their existence is in danger due to several factors such as massive urbanization, industrialization, etc. Governments all over the world are striving to develop monitoring mechanisms to save the forests. Several programmes have been initiated by Pakistani government for forest cultivations, s...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Muhammad Rizwan Khalid [BSCS-6] Syed Abbas Hussain Naqvi [BSCS-6]


48 .
RXKeep - Physicians Practice Management Solution:

Rxkeep for doctors:
 Doctors will be available to prescribe in much faster and easier way through a web and mobile apps.
 Doctors will be able to see patient’s previous record in an organized form.
 Allowing clinics to keep the complete track of their monthly patient visits.
 Rxkeep will decrease the need of man power in clinics to manage receipts and pre checkup registrations.
 If a pa...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Bilal Khalid [BSCS-6] Waqas Yaseen [BSCS-6] Muneeb Ishaq [BSCS-6]


49 .
Crop Health Analysis Using Deep Learning:

Crop Health Analysis Using Deep Learning


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Ahmad Amjad Mughal [BSCS-6] Saqib Ali Khan [BSCS-6] Faizan E Muhammad [BSCS-6]


50 .
Slum Mapping in Aerial Imagery Using Convolution Neural Networks:

Slum Mapping in Aerial Imagery Using Convolution Neural Networks


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Syed Waleed Hyder [BESE-7] Hamna Moieez [BESE-7]


51 .
Autonomous Landing of fixed wing UAV on runway using computer vision techniques.:

Since there is no pilot onboard in UAV’s to land in emergency situations (like loss of link, navigation aid failure etc.). Thus an autonomous computer vision based solution can cater to the needs. In the project, state-of-the-art object detection algorithms based on deep learning will be optimized and implemented on Zynq FPGA based embedded platform. The output of the embedded platform will be a...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Muhammad Gohar Javed [BEEE-8] Minahil Raza [BEEE-8]


52 .
Multi modal Deep Learning for Scene Understanding:

The mapping of multiple modalities to a shared latent space has resulted in
improved scene understanding because the information enriches learned representations help in explaining the visual content. Due to recent advancements
in this area [1–4], we see a surge in multimodal tasks such as image caption
generation [5–9], visual question answering [10, 11], and audio-visual correspondence [12–1...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Muhammad Kamran Janjua [BSCS-6] Raja Hasnain Anwar [BSCS-6]


53 .
DeepEEG: A deep learning based platform for EEG signal analysis:

This project will develop deep learning software for analysis of EEG signals. The objective is to develop software which can classify normal and abnormal EEG signals. Existing online datasets will be used for algorithm development. The possibility of employing inhouse EEG data will also be explored (time permitting).


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Hassan Aqeel Khan [EE]
Co-Advisor
Adnan Ul-Hasan [ECM] Faisal Shafait [DoC]
Students
Rahat Ul Ain [BESE-7] Hira Tanveer [BESE-7]


54 .
Internet of Things (IoT) enabled surface water pollution detection :

Water is one of the primary requisites and essential for sustaining the quality of life on Earth. In Pakistan, its importance is more than ordinary due to the agrarian nature of the economy, however, Pakistan still relies on traditional systems due to challenges such as lack of literacy, the institutional capacity to deliver technology, and economic constraints. The traditional tools for water qu...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Co-Advisor
Faisal Shafait [DoC] Adnan Ul-Hasan [ECM]
Students
Hamza Khurshid [BESE-7] Noor Alvi [BESE-7]


55 .
Water Quality Data Extraction from Handwritten Documents Using Deep Learning:

In Pakistan’s government offices, the data is usually manually recorded in hard registers. It is often in tabular form or in the form of running hand written text. The tables present summarized and structured information to the reader, which makes table’s information extraction an important part of document understanding applications. However it is a hard problem not only because of the large var...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Rafia Mumtaz [DoC]
Co-Advisor
Muhammad Imran Malik [DoC] Adnan Ul-Hasan [ECM] Faisal Shafait [DoC]
Students
Syed Muhammad Daniyal Khalid [BESE-7] Nosherwan Akram [BESE-7]


56 .
Deployment of Deep Neural Networks on FPGAs:

Deep Neural Networks are computationally expensive computational machines. An emerging trend in this domain is to run these algorithms on stand-alone machines using FPGAs. Several FPGA vendors claims to run deep neural networks on their architectures. Current research aims to further develop this idea.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Syed Tihaam Ahmad [BEEE-8] Abdullah Ashfaq [BEEE-7]


57 .
Easy Tax Filing:

Regarding the current situation of tax collection in Pakistan, where only 0.57% of the total population pay taxes, is very low. One of the reasons for this low figure is the complexity of tax filing. The aim is to make the tax filing easy by making the whole process easy and interactive such that an individual will be able to file his taxes by himself through a chat bot. Another aim of the projec...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2019
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Arifullah Jan [BSCS-6] Saqib Shakeel [BSCS-6] Noman Mustafa [BSCS-6]


58 .
Speech Information Component Analysis:

This project deals with extracting speaker-specific information, emotion information and verbal information from speech signal using single but dedicated deep neural network. Different information components will be clustered out in the feature space.


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2018
Status: Completed
Advisor
Ahmad Salman [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Uzair Zia [BESE-6] Ahmed Sarfraz [BESE-6] Aziz Ur Rehman [BESE-6]


59 .
CONTEXT AWARE RECOMMENDATION SYSTEM FOR CHATBOTS:

Maintaining the link of past conversations with the current one.

Problem?
Most of the online shopping websites do not recognize the users when they visit the portal again. Due to this reason, user has to specify his product/item attributes again.

Solution?
To overcome this problem, there is a need to develop a context aware system that can re-identify the user, maintain user stream, kee...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Seemab Latif [DoC]
Students
Raaiha Humayun Kabir [BESE-6] Tayyeba Muhammad Khan [BESE-6] Bisma Pervaiz [BESE-6]


60 .
Open-world Extension to Knowledge Graph Completion Models:

In NLP, a thriving research topic is learning from large-scale knowledge
graphs such as Wikidata, DBPedia, WordNet, or Freebase. These graphs
contain large scales of triple-based facts such as (Obama, born_in,
Hawai). Several models have been proposed for representation learning of
the graphs' entities and relations, which makes it possible to assess
the plausibility of facts not yet present...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Seemab Latif [DoC]
Students
Haseeb Shah [BESE-6] Abdul Qadir [BESE-6]


61 .
Chaperone:

Chaperone


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Umer Imran [BEEE-7] Muhammad Faisal Zahoor [BEEE-7] Muhammad Haroon [BEEE-7]


62 .
Face Detection and Recognition in Camera Feeds :

Today there is a great need of real time intelligent systems capable of detecting and recognizing suspicious/ unknown persons as and when they enter into the sight of a surveillance camera. Some hi-tech companies, e.g., Nayatel in Pakistan, Hikvision and Amazon in the US and Europe, have been providing their customers with full integrated 24/7 surveillance systems through IP cameras that detect m...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Hafiz Hamza Hafeez [BSCS-5] Hafiz Muhammad Taha Khan [BSCS-5]


63 .
Deep Learning Based Forest Change Detection:

Pakistan is among one of the worst countries that are affected by forest degradation and deforestation and if appropriate measures are not taken, the country is likely to lose all of its forests in the next thirty to fifty years. Forest management faces many challenges in Pakistan. The Forestry department in Pakistan is ill-equipped to counter these challenges. It lacks human and financial resour...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Muhammad Shahzad [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Annus Zulfiqar [BEEE-7] Osama Yaseen [BEEE-7]


64 .
Hierarchical Softmax for fine-grained classification:

Purpose of the Project
To research and develop a training/prediction softmax layer / algorithm within tensorflow to have hierarchical categories.

Aim
We aim to add a layer in tensorflow i.e. hierarchical softmax which would train/predict classes of input image in hierarchical fashion, for e.g. Dog category would have sub classes of german-shephard, Labrador, etc. for reference, see YOLO v2 ...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Fatima Hassan [BSCS-5] Mohammad Uzair [BSCS-5]


65 .
Hardware Aware Training of Deep Networks:

Hardware Aware Training of Deep Networks


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Ussama Zahid [BEEE-7] Muhammad Umar [BEEE-7]


66 .
Deep learning for Drone Manuevering:

This project aims at exploring deep learning techniques for automatic maneuvering of drones.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2018
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Sohaib Zahid [BESE-6] Muhammad Ali [BESE-6] Umar Khan [BESE-6]


67 .
Table Detection and Structure Extraction from Document Images:

Table spotting from scanned images or PDFs is a major step in most of the information extractions systems. However, reliably detecting tables across a variety of layouts is a challenging problem. Once a table is spotted, the next step is to parse the table into rows and columns so that information can be extracted in a meaningful way. This project aims at developing a machine learning algorithm t...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Tooba Imtiaz [BEEE-6] Shah Rukh Qasim [BEEE-6]


68 .
Automatic Vehicle Surveillance using Embedded Vision:

This project aims at developing the hardware and software for a comprehensive stand-alone solution for vehicle detection and recognition under real-world conditions.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Maaz Jamal [BEEE-6] Hatim Ali [BEEE-6] Sheikh Umaid Bin Zubair [BEEE-6]


69 .
Automatic Shopping Cart Population from Camera Captured Images:

This project aims at developing algorithms for OCR, Information Extraction, and Data Science to automatically extract information from a camera captured image of a shopping list.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Nauman Mustafa [BEEE-6] Umair Bin Tahir [BEEE-6] Talha Rehman [BEEE-6]


70 .
Deep Learning on FPGA:

Deep learning algorithms are not only resource intensive but also face challenges in deployment in real time applications. This project aims at implementing deep learning architectures, specifically Convolutional Neural Networks, on FPGA and study their energy consumption and performance behaviour.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [EE]
Students
Hamza Shafqaat [BEEE-6] Amna Masood [BEEE-6] Zainab Tareen [BEEE-6]


71 .
Online Learning for Address Recognition on Envelops:

A major bottleneck in postal services workflow in Pakistan is the manual entry process for all the post to route it effectively. In this project, we aim to develop a deep learning based system for recognition of addresses from the envelops. English addresses will be recognized in this project, both in machine printed and handwritten forms.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Adnan Ul-Hasan [ECM]
Students
Muhammad Ferjad Naeem [BEEE-6] Noor Ul Sehr Zia [BESE-5] Syed Muhammad Kumail Raza [BESE-5]


72 .
Vehicle Detection and Recognition from Aerial Images:

Unmanned Aerial Vehicles (UAVs) or Drones are commonly used these days for surveillance and threat identification. However, with the current technology, there is a need of a human operator to constantly watch the video streams from these UAVs. This human operator involvement, which is prone to errors and negligence, may be reduced by having an automated system to detect threats from the aerial im...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Muhammad Noman Shafqat [BESE-5] Mahum Tariq [BESE-5] Hassan Mahmood [BESE-5]


73 .
Real Time Runway Detection from Drones using Computer Vision:

A major issue in UAVs / Drones is encountered when they loose signals from the base station and have to autonomously land. Computer vision algorithms can be used to detect roads or other regions where drone can land itself safely.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Muhammad Gulzain Ali Khan [BESE-5] Muhammad Umer Javaid [BESE-5] Khadija Butt [BESE-5]


74 .
Incremental Learning of Object Detectors using Limited Training Data:

Object detectors in practice find it hard to generalize due to the wide variety of object categories present in real world environments. Incremental learning aims at providing more control to the end users of the object recognition technology so that they can add more object categories to be recognized without the intervention of the machine learning expert. This thesis will focus on indoor objec...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [DoC]
Students
Khurram Javed [BESE-5] M. Talha Paracha [BESE-5]


75 .
Tracking Fish in the Wild:

Fish tracking in underwater images is a major challenge due to the diverse motion patterns of fish in 3D environments. Existing tracking algorithms do not perform well when applied on tracking fish. This project aims at using deep learning for tracking fish.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2017
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Harim Akhtar [BEEE-6] Nouman Sial [BEEE-6] Hassam Khan [BEEE-6]


76 .
Suicide vest detection using deep learning:

Please follow the link

https://docs.google.com/a/seecs.edu.pk/document/d/11G8vk6-5F_MrXtCkYn2KxcoPvTgmrhx_uAux6h8ZUbc/edit?usp=sharing


Project Level: UG
Project Type: FYP
KnowledgeArea: Computational Science
Year: 2017
Status: Completed
Advisor
Wajahat Hussain [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Syed Abbas Tariq Hasany [BSCS-4] Muhammad Hamza Nasim [BSCS-4] Hammad Abdullah [BSCS-4]


77 .
Machine Learning based Load Forecasting Tool for Smart Grid Enabling Technology:

Note: *This is a Joint Research Project between NUST and Arizona State University, funded by USAID*

Ever wonder what makes a Smart Grid smarter than a Conventional Grid!!! A conventional power system can only control the source side in order to match the demand. However a smart grid enables "Demand Side Management" through which the demand side can be controlled in order to achieve the optimal...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2017
Status: Completed
Advisor
Syed Raza Kazmi [ECM]
Co-Advisor
Faisal Shafait [DoC]
Students
Waqas Javed [BSCS-4] Mohsin Ammar [BSCS-4] Ali Farooq [BSCS-4]


78 .
SmartPath:

Patients in remote areas of Pakistan generally do not have access to high quality disease screening and diagnosis. This project will employ machine learning enhance pathology images collected from standard off-the-shelf analog microscopes. At the first stage images quality will be enhanced using machine learning and image processing algorithms. The enhance images will then be used for screening a...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2017
Status: Completed
Advisor
Hassan Aqeel [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
M Asjid Tanveer [BEEE-6] Haroon Rashid [BEEE-6] Haider Tariq [BEEE-6]


79 .
Real-time Semantic/Scene Analysis Using Deep Learning:

Semantic analysis or scene analysis is emerging field in computer vision with application in autonomous robotics, autonomous vehicles artificial vision for visually impaired people. Semantic analysis involves identifying/classifying various objects in video stream as shown in Figure-1. Based on the detected objects actuations can be generated in the form of control signals or speech signal to inf...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2017
Status: Completed
Advisor
Ahmad Salman [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Armaghan Saleem [BEEE-6] Saad Mahmood [BEEE-6] Arbaz Mubasher [BEEE-6]


80 .
Computer Vision based Automatic Landing for Drones / Unmanned Air Vehicles (UAV):

This project aims at automatic detection and tracking of lane markings / road boundaries in real-time from aerial views obtained from cameras mounted on drones / UAVs. The goal is to assist the drone / UAV in emergency landing in unknown terrains based on visual sensors.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Omar Arif [DoC]
Students
Ayesha Yaqub [BESE-4] Taimoor Tariq [BESE-4] Haider Ali Agha [BESE-4]


81 .
Roadway Intelligence:

A large number of surveillance cameras have been installed across the city of Islamabad. This project will aim at automatic vehicle detection, classification, and tracking across the camera systems using advanced computer vision and machine learning algorithms.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Omar Arif [DoC]
Students
Kuldeep Kumar [BSCS-3] Muhammad Zaheer [BSCS-3]


82 .
Underwater Imaging for Fish Fauna Estimation:

This project aims at developing hardware and software for fish fauna estimation. An underwater imaging system will be developed to record video data of underwater environment. Then, software will be developed for various algorithmic steps including fish detection, fish tracking, and fish species identification.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Abdul Hannan Khan [BSCS-3] Amal Mubashar [BSCS-3]


83 .
Active Learning for Fish Tracking in Unconstrained Environments:

This project aims at developing hardware and software for fish fauna estimation. An underwater imaging system will be developed to record video data of underwater environment. Then, software will be developed for various algorithmic steps including fish detection, fish tracking, and fish species identification.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Syed Hassaan Tauqeer [BSCS-3] Rafay Ahmed Khan [BSCS-3]


84 .
Cargar - The Next Generation Motorbike Taxi:

Cargar is a SEECS based startup offering motorbike taxi service, unique in its accessible market. It has been features across a number of news and media channels due to its innovative product. The project involves working with the startup team to develop functionalities for:
Key operational services
GPS Tracking system
Virtual Assistant (Microsoft Bot Framework)
Other native functionalities...


Project Level: UG
Project Type: FYP
KnowledgeArea: Platform-based Development
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Imran Malik [DoC]
Students
Muddassir Ahmed Khan [BEEE-5]


85 .
Colored Garments Image Search and Retrieval based on Visual Similarity:

This project involves developing and testing an automated computer vision based system that can establish similarity between two images of garments based on their visual similarity.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Ahmad Salman [EE]
Students
Fatima Arshad [BESE-4] Ayesha Khalid [BESE-4]


86 .
TeleDoc: A Portable Device for Remote Diagnostic Screening of Patients:

This project involves hardware and software for remote medical diagnosis and screening applications. The device will integrate basic interfaces for measuring vital health signs and transmitting them over communication channels to remotely sitting medical professional. Android app will be develop to interface the doctor and the patient and integrate the device signals with the app.


Project Level: UG
Project Type: FYP
KnowledgeArea: Platform-based Development
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [EE]
Students
Ramsha Waseem [BESE-4] Nyma Altaf [BESE-4]


87 .
TeleDoc: A Portable Device for Remote Diagnostic Screening of Patients:

This project involves hardware and software for remote medical diagnosis and screening applications. The device will integrate basic interfaces for measuring vital health signs and transmitting them over communication channels to remotely sitting medical professional. Processing of all acquired data from medical sensors including image and video data will be done on the embedded device.


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2016
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Muhammad Shahzad [EE]
Students
Sohaib Nasir [BEEE-5] Muhammad Abdullah Anjum [BEEE-5] Abdul Rahman Bin Saad [BEEE-5]


88 .
BA-ILM: Business Analytics for Industrial IoT using LoRa Sensor Network:

Utilizing LoRaWAN (Low Power Wide Area Network) for industrial IoT applications and BI tools to make sense of data.


Project Level: UG
Project Type: FYP
KnowledgeArea: Electronics
Year: 2016
Status: Completed
Advisor
Hammad Mehmood Cheema [ECM]
Co-Advisor
Faisal Shafait [DoC]
Students
Syed Qambar Ahmed Rizvi [BEEE-5] Syed Ahmed Hussain Naqvi [BESE-4] Maria Aftab [BEEE-5]


89 .
Hyper-spectral Image Segmentation and Verification:

Hyper-spectral document analysis is an active area of research where the current project would aim at solving the problem of text/non-text segmentation and signature verification.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Muhammad Imran Malik [DoC]
Co-Advisor
Faisal Shafait [DoC]
Students
Mohammad Hassan Uz Zaman [BSCS-3]


90 .
Netlytics - Predictive analysis of SDN log data.:

Most modern network systems generate massive amounts of log data. The information in these log files is often too large for the human expert to process quickly. As a result the monitoring approaches being employed currently are REACTIVE i.e., log data is examined after a problem takes place. The objective of this project is to develop (artificially) intelligent tools for real-time (or near real-t...


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2016
Status: Completed
Advisor
Hassan Aqeel [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Ahad Mahmood [BESE-4] Rana Awais [BESE-4] Muhammad Moazzam [BESE-4]


91 .
Dengue-Detector: An expert system for early dengue diagnosis:

Dengue is a rapidly spreading disease especially in the tropical regions and even more so in the rural areas. It is the most common arthropod-borne infection worldwide especially in third world countries like Pakistan due to substandard housing and poor sanitary conditions. According to a report by World Health Organization (WHO), almost 50 million people are infected by dengue annually worldwide...


Project Level: UG
Project Type: FYP
KnowledgeArea: DSSP
Year: 2015
Status: Completed
Advisor
Muhammad Shahzad [EE]
Co-Advisor
Faisal Shafait [DoC]
Students
Maria Riaz [BEEE-4] Aneeqa Ejaz [BEEE-4] Bareera Dar [BEEE-4]


92 .
GreenPi:

A raspberry pi based product that monitors the plant's environment and guides through messages on cell phone about the requirements of its growth depending on environment conditions


Project Level: UG
Project Type: FYP
KnowledgeArea: Networking and Communications
Year: 2015
Status: Completed
Advisor
Sana Khalique [DoC]
Co-Advisor
Anis ur Rahman [DoC]
Students
Noman Rafi [BSCS-2] Hafiz Hasan Ishtiaq [BSCS-2] Muhammad Hamza [BSCS-2]


93 .
OptiNets:

The objective is to optimally orchestrate a network’s resources such that a tenant’s requirements are
met while also considering the churn and elasticity both in the networking environment.
We have different optimality constraints for this:
? Minimize migration cost when a new tenant comes in,
? Maximize free space,
? Intelligence in platform for load balancing,
? Automated Orchestration.
...


Project Level: UG
Project Type: FYP
KnowledgeArea: Networking and Communications
Year: 2015
Status: Completed
Advisor
adnan khalid [EE]
Co-Advisor
Junaid Qadir [EE]
Students
Bilal Zahid [BSCS-2] Shayan Javeed [BSCS-2]


94 .
Automation of RFID Based Attendance Management System:

SEECS has a fingerprint-based attendance management system installed for its staff. The system is comprised of multiple fingerprint recognition devices available at SEECS, IAEC, and RIMMS. A staff member is required to mark his/her attendance at any such device in morning, and then again mark before leaving in evening.
However, a major problem with this system is that the attendance data is manu...


Project Level: UG
Project Type: FYP
KnowledgeArea: Information Management
Year: 2015
Status: Completed
Advisor
Muhammad Muneeb ULLAH [DoC]
Co-Advisor
Mian Muhammad Hamayun [DoC]
Students
Muhamamd Abdullah Khan [BSCS-2] Alishpa Ahmed [BSCS-2] Muneeb Suleman [BSCS-2] Aimal Khan [BSCS-2]


95 .
EpiWear: A Wearable for Accurate and Timely Detection of Epileptic Seizures:

Epi-Wear: Epileptic Seizure Detection and Prevention


Project Level: UG
Project Type: FYP
KnowledgeArea: Electronics
Year: 2015
Status: Completed
Advisor
Hammad Mehmood Cheema [ECM]
Co-Advisor
Faisal Shafait [DoC] Awais Mehmood Kamboh [EE]
Students
Waqas Ahmad [BEEE-4] Abdullah Ahmed [BEEE-4] Shoaib Ahmed Siddiqui [BSCS-2] Muhammad Jazib Khan [BEEE-4]


96 .
Computer Vision for Driving Safety Analysis:

The goal of this project is to develop a real-time algorithm that can detect and track lane markings in a video. The video is captured with a smart phone that is mounted on the dashboard of the vehicle. Frequent lane changes would indicate unsafe driving behaviour.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2015
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Omar Arif [DoC]
Students
Anam Ahmed Khan [BSCS-2] Aman Irshad [BSCS-2] Ibrar Yunus [BSCS-2]


97 .
Underwater Imaging for Fish Fauna Estimation:

This project aims at developing hardware and software for fish fauna estimation. An underwater imaging system will be developed to record video data of underwater environment. Then, software will be developed for various algorithmic steps including fish detection, fish tracking, and fish species identification.


Project Level: UG
Project Type: FYP
KnowledgeArea: Intelligent Systems
Year: 2015
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Anis ur Rahman [DoC] Ahmad Salman [EE]
Students
Ilsa Niazi [BEEE-4] Isha Lodhi [BEEE-4] Saba . [BEEE-4]


98 .
Analytics and Visualization in Openstack:

Openstack is an opensource cloud computing software for public and private clouds. Currently, Openstack has a robust data collection and logging mechanism but that data is only used by system administrators and other Openstack modules. This project aims to provide an intuitive UI for visualizing the cloud and its virtualized components along with Analytics engine based on machine learning to pred...


Project Level: UG
Project Type: FYP
KnowledgeArea: Networking and Communications
Year: 2015
Status: Completed
Advisor
Faisal Shafait [DoC]
Co-Advisor
Junaid Qadir [EE] Muhammad Usman Ilyas [EE]
Students
Syed Mohammad Aunn Raza [BSCS-2] Hunain Arif [BSCS-2]


Journal

(1.) Abdul Wahab, Muhammad Anas Tahir, Naveed Iqbal, Adnan Ul-Hasan, Faisal Shafait, Syed Muhammad Raza Kazmi, , "A Novel Technique for Short-Term Load Forecasting using Sequential Models and Feature Engineering", IEEE Access, Vol. 9 , No. 9, PP. 96221 - 96232, Jun, 2021. IF: 3.367
(2.) Junaid Younas , Muhammad Imran Malik, Sheraz Ahmed, Faisal Shafait, Paul Lukowicz , "Sense the pen: Classification of online handwritten sequences (text, mathematical expression, plot/graph)", Expert Systems with Applications, Vol. 172 , No. 172, Jan, 2021.
(3.) Junaid Younas , Muhammad Shoaib Ahmed Siddiqui, Mohsin Munir, Muhammad Imran Malik, Faisal Shafait, Paul Lukowicz, Sheraz Ahmed , "Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks", Applied Sciences, Vol. 10 , No. 18, Sep, 2020.
(4.) Salah Ud Din , Naveed Akhtar, Shahzad Younis, Faisal Shafait, Atif Mansoor, Muhammad Shafique , "Steganographic Universal Adversarial perturbations", Pattern Recognition Letters , Vol. 135 , No. 135, PP. 146-152, Apr, 2020.
(5.) Ahsan Jalal , Ahmad Salman, Ajmal Mian, Mark Shortis, Faisal Shafait , "Fish detection and species classification in underwater environments using deep learning with temporal information", Ecological Informatics , Vol. 57 , No. 101088, Apr, 2020. IF: 2.511
(6.) Zohaib Khan, Faisal Shafait, Ajmal Mian , "Converting A Common Low-Cost Document Scanner Into A Multispectral Scanner ", SENSORS, Vol. 19 , No. 14, Jul, 2019. IF: 3.031
(7.) Muhammad Naseer Bajwa, Muhammad Imran Malik, Shoaib Ahmad Siddiqui, Andreas Dengel, Faisal Shafait, Wolfgang Neumeier, Sheraz Ahmed , "Two-Stage Framework For Optic Disc Localization And Glaucoma Classification In Retinal Fundus Images Using Deep Learning ", BMC Medical Informatics and Decision Making, Vol. 19 , No. 136, Jul, 2019.
(8.) Ahmad Salman, Salman Maqbool, Abdul Hannan Khan, Ahsan Jalal, Faisal Shafait , "Real-Time Fish Detection In Complex Backgrounds Using Probabilistic Background Modelling", Ecological Informatics, Vol. 51 , No. 1-200, Feb, 2019.
(9.) Ahmad Salman, Shoaib Ahmad Siddiqui, Faisal Shafait, Ajmal Mian, Mark R. Shortis,Khawar Khurshid, Adrian Ulges, and Ulrich Schwanecke , "Automatic fish detection in underwater videos by a deepneural network-based hybrid motion learning system", ICES Journal of Marine Science, Vol. 76 , No. 1, Jan, 2019. IF: 3.367
(10.) Hasan F. M. Zaki, Faisal Shafait, Ajmal Mian , "Viewpoint Invariant Semantic Object And Scene Categorization With RGB-D Sensors", Autonomous Robots, Vol. 43 , No. 1, Jan, 2019.
(11.) Jameel Malik, Ahmed Elhayek, Sheraz Ahmed, Faisal Shafait, Muhammad Imran Malik and Didier Stricker , "3DAirSig: A Framework For Enabling In-Air Signatures Using A Multi-Modal Depth Sensor", Sensors, Vol. 18 , No. 11, Nov, 2018.
(12.) Muhammad Uzair, Faisal Shafait, Bernard Ghanem, Ajmal S. Mian , , "Representation learning with deep extreme learning machines for efficient image set classification", Neural Computing and Applications, Vol. 30 , No. , PP. 1211-1233, Aug, 2018. IF: 4.213
(13.) Syed Zulqarnain Gilani, Ajmal S. Mian, Faisal Shafait, Ian D. Reid , , "Dense 3D Face Correspondence", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40 , No. , PP. 1584-1598, Jul, 2018. IF: 9.455
(14.) Shoaib Ahmed Siddiqui , Ahmad Salman, Muhammad Imran Malik, Faisal Shafait, Ajmal Mian, Mark R Shortis, Euan S Harvey , "Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data", ICES Journal of Marine Science, Vol. 15 , No. 1, PP. 374-389, Feb, 2018. IF: 2.76
(15.) Saeeda Naz , Arif Iqbal Umar, Riaz Ahmad, Imran Siddiqi, Saad Bin Ahmed, Muhammad Imran Razzak, Faisal Shafait , "Urdu Nastaliq recognition using convolutional–recursive deep learning", Neurocomputing, Vol. 243 , No. , PP. 80-87, Jun, 2017. IF: 3.317
(16.) Hasan F.M. Zaki, Faisal Shafait, Ajmal Mian , , "Learning a deeply supervised multi modal RGB embeding for semantics scene and object category recognition", Robotics and Autonomous system, Vol. 92 , No. , PP. 41-52, Jun, 2017. IF: 1.950
(17.) Faisal Shafait, Euan S. Harvey, Mark R. Shortis, Ajmal Mian Mehdi Ravanbakhsh, James W. Seager, Philip F. Culverhouse, Danelle E. Cline, Duane R. Edgington , , "Towards automating under water measurements of fish length: a comparison of semi automatic and manual stereo-video", ICES Journal of Marine Science, Vol. 74(6) , No. , PP. 1690-1701, Jun, 2017. IF: 2.760
(18.) Naveed Akhtar, Faisal Shafait, Ajmal S. Mian , , "Efficient classification with sparsity augmented collaborative representation.", Pattern Recognition , Vol. 65 , No. , PP. 136-145, May, 2017. IF: 4.582
(19.) Naveed Akhtar, Faisal Shafait, Ajmal S. Mian , , "Discriminative Bayesian Dictionary Learning for Classification ", IEEE Trans. Pattern Analysis, Vol. 38 , No. , PP. 2374-2388, Dec, 2016. IF: 8.329
(20.) Faisal Shafait, Ajmal Mian, Mark Shortis, Bernard Ghanem, Phil F. Culverhouse, Duane Edgington, Danelle Cline, Mehdi Ravanbakhsh, James Seager, Euan S. Harvey , , "Fish identification from videos captured in uncontrolled underwater environments ", ICES Journal of Marine Science, Vol. 73 , No. , PP. 2737-2746, Nov, 2016. IF: 2.760
(21.) Ahmad Salman , Ahsan Jalal, Faisal Shafait, Ajmal Mian, Mark Shortis, James Seager and Euan Harvey , "Fish species classification in unconstrained underwater environment based on deep learning", Limnology and Oceanography: Methods, Vol. 14 , No. 9, PP. 570-585, May, 2016. IF: 1.992
(22.) Saeeda Naz, Arif Iqbal Umar, Riaz Ahmad, Muhammad Imran Razzak, Sheikh Faisal Rashid, Faisal Shafait , , "Urdu Nastaliq Text Recognition using Implicit Segmentation based on Multi-Dimensional Long Short Term Memory Neural Networks", SpringerPlus, Vol. , No. , PP. , Jan, 2016. IF: 0.982
(23.) Zohaib Khan , Faisal Shafait, Ajmal Mian , "Joint Group Sparse PCA for Compressed Hyperspectral Imaging", IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol. 24 , No. 12, PP. 4934-4942, Dec, 2015. IF: 3.625
(24.) Andrew J. O. Whitehouse , Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian, Diana Weiting Tan, Murray T. Maybery, Jeffrey A. Keelan, Roger Hart, David J. Handelsman, Mithran Goonawardene, Peter Eastwood , "Prenatal testosterone exposure is related to sexually dimorphic facial morphology in adulthood", Proceedings of The Royal Society B, Vol. 282 , No. 1816, PP. 282 20151351, Sep, 2015. IF: 5.05
(25.) Syed Zulqarnain Gilani, Diana Tan, Suzanna N Russell-Smith, Murray T Maybery, Ajmal Mian, Peter R Eastwood, Faisal Shafait, Mithran Goonewardene, Andrew Whitehouse, , , "Sexually dimorphic facial features vary according to level of autistic-like traits in the general population", Journal of Neurodevelopmental Disorders, Vol. 7 , No. 14, PP. , Apr, 2015. IF: 3.705
(26.) Naveed Akhtar, Faisal Shafait, and Ajmal Mian, , , "Futuristic greedy approach to sparse unmixing of hyperspectral data", IEEE Transactions on Geoscience and Remote Sensing, Vol. 53 , No. 4, PP. 2157-2174, Apr, 2015. IF: 2.933
(27.) Mehdi Ravanbakhsh, Mark R. Shortis, Faisal Shafait, Ajmal Mian, Euan S. Harvey ,James W. Seager, , , "Automated Fish Detection in Underwater Images Using Shape-Based Level Sets", The Photogrammetric Record, Vol. 30 , No. 149, PP. 46-62, Mar, 2015. IF: 1.377
(28.) Zohaib Khan, Faisal Shafait, Ajmal Mian, , , "Automatic Ink Mismatch Detection for Forensic Document Analysis", Pattern Recognition, Vol. 48 , No. 11, PP. 3615-3626, Jan, 2015. IF: 2.584
(29.) Muhammad Uzair , Arif Mahmood, Faisal Shafait, Christian Nansen, Ajmal Mian , "Is spectral reflectance of the face a reliable biometric?", Optics Express, Vol. 23 , No. 12, PP. 15160-15173, Jan, 2015. IF: 3.488
(30.) Renwu Gao, Seiichi Uchida, Asif Shahab, Faisal Shafait, Volkmar Frinken, , , "Visual Saliency Models for Text Detection in Real World", PLOS ONE, Vol. 9 , No. 12, PP. e114539, Dec, 2014. IF: 3.534
(31.) Syed Zulqarnain Gilani, Kathleen Rooney, Faisal Shafait, Mark Walters, Ajmal Mian , , "Geometric Facial Gender Scoring: Objectivity of Perception", PLOS ONE, Vol. 9 , No. 6, PP. e99483 , Jun, 2014. IF: 3.534
(32.) Matthias Reif, Faisal Shafait, , , "Efficient Feature Size Reduction via Predictive Forward Selection", Pattern Recognition, Vol. 47 , No. 4, PP. 1664-1673 , Apr, 2014. IF: 2.584
(33.) Haider Ali, Faisal Shafait, Eirini Giannakidou, Athena Vakali, Nadia Figueroa, Theodoros Varvadoukas, Nikolaos Mavridis, , , "Contextual Object Category Recognition for RGB-D Scene Labeling", Robotics and Autonomous Systems, Vol. 62 , No. 2, PP. 241-256, Feb, 2014. IF: 1.105
(34.) Matthias Reif, Faisal Shafait, Markus Goldstein, Thomas M. Breuel, Andreas Dengel , , "Automatic Classifier Selection for Non-Experts", Pattern Analysis and Applications, Vol. 17 , No. 1, PP. 83-96, Feb, 2014. IF: 0.814
(35.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Automatic Authentication of Color Laser Print-Outs Using Machine Identification Codes", Pattern Analysis and Applications, Vol. 16 , No. 4, PP. 663-678, Nov, 2013. IF: 0.814
(36.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Text-Line Examination for Document Forgery Detection", International Journal on Document Analysis and Recognition, Vol. 16 , No. 2, PP. 189-207, Jun, 2013. IF: 0.8
(37.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Coupled Snakelets for Curled Text-Line Segmentation from Warped Document Images", International Journal on Document Analysis and Recognition, Vol. 16 , No. 1, PP. 33-53, Mar, 2013. IF: 0.8
(38.) Matthias Reif, Faisal Shafait, Andreas Dengel, , , "Meta-Learning for Evolutionary Parameter Optimization of Classifiers", Machine Learning, Vol. 87 , No. 3, PP. 357-380, Mar, 2012. IF: 1.454
(39.) Janick V. Frasch, Aleksander Lodwich, Faisal Shafait, Thomas M. Breuel, , , "A Bayes-True Data Generator for Evaluation of Supervised and Unsupervised Learning Methods", Pattern Recognition Letters, Vol. 32 , No. 11, PP. 1523-1531, Aug, 2011. IF: 1.034
(40.) Faisal Shafait, Thomas M. Breuel, , , "The Effect of Border Noise on the Performance of Projection Based Page Segmentation Methods", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33 , No. 4, PP. 846-851, Aug, 2011. IF: 4.908
(41.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Combined Orientation and Skew Detection Using Geometric Text-Line Modeling", International Journal on Document Analysis and Recognition, Vol. 13 , No. 2, PP. 79-92, Jan, 2010. IF: 1.020
(42.) Faisal Shafait, Joost van Beusekom, Daniel Keysers, Thomas M. Breuel, , , "Document Cleanup Using Page Frame Detection", International Journal on Document Analysis and Recognition, Vol. 11 , No. 2, PP. 81-96, Nov, 2009. IF: 0.909
(43.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , "Response to 'Projection Methods Require Black Border Removal'", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31 , No. 4, PP. 763-764, Apr, 2009. IF: 4.378
(44.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Adaptive Binarization of Unconstrained Hand-Held Camera-Captured Document Images", Journal of Universal Computer Science, Vol. 15 , No. 8, PP. 3343-3363, Jan, 2009. IF: 0.669
(45.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , "Performance Evaluation and Benchmarking of Six Page Segmentation Algorithms", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30 , No. 6, PP. 941-954, Jun, 2008. IF: 5.960

Conference

(1.) Umar Khan, Sohaib Zahid, Muhammad Asad Ali, Adnan Ul-Hasan, Faisal Shafait , "TabAug: Data Driven Augmentation for Enhanced Table Structure Recognition ", Proceedings of the International Conference on Document Analysis and Recognition, Sep, 2021, Lausanne , Switzerland.
(2.) Faiza Rehman,Hira Masood,Adnan Ul-Hasan,Raheel Nawaz,Faisal Shafait , "An Intelligent Context Aware Recommender System for Real-Estate", Proceedings of the 3rd Mediterranean Conference on Pattern Recognition and Artificial Intelligence, Dec, 2019, Istanbul , Turkey.
(3.) Junaid Younas, Syed Tahseen Raza Rizvi, Muhammad Imran Malik, Faisal Shafait, Paul Lukowicz, Sheraz Ahmed , "FFD: Figure and Formula Detection from Document Images", Proceedings of the DICTA , Dec, 2019, Perth , Australia.
(4.) Javeria Akbar, Muhammad Shahzad, Muhammad Imran Malik, Adnan Ul-Hasan, Faisal Shafait , "Runway Detection And Localization In Aerial Images Using Deep Learning", Proceedings of the DICTA 2019, Dec, 2019, Perth , Australia.
(5.) Ammad Ul Islam, Muhammad Jaleed Khan, Khurram Khurshid, Faisal Shafait , "Hyperspectral Image Analysis For Writer Identification Using Deep Learning", Proceedings of the DICTA 2019, Dec, 2019, Perth , Australia.
(6.) Muhammad Ali Shahzad, Rabeya Noor, Sheraz Ahmad, Ajmal Mian, Faisal Shafait , "Feature Engineering meets Deep Learning: A Case Study on Table Detection in Documents", Proceedings of the DICTA 2019, Dec, 2019, Perth , Australia.
(7.) Annus Zulfiqar, Adnan Ul-Hasan, Faisal Shafait: , "Logical Layout Analysis using Deep Learning", Proceedings of the DICTA 2019, Dec, 2019, Perth , Australia.
(8.) Saqib Ali Khan, Syed Muhammad Daniyal Khalid, Muhammad Ali Shahzad, Faisal Shafait , "Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Sep, 2019, Sydney , Australia.
(9.) Shah Rukh Qasim, Hassan Mahmood, and Faisal Shafait , "Rethinking Table Recognition using Graph Neural Networks", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Sep, 2019, Sydney , Australia.
(10.) Muhammad Jaleed Khan, Khurram Khurshid, Faisal Shafait , "A Spatio-Spectral Hybrid Convolutional Architecture for Hyperspectral Document Authentication", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Sep, 2019, Sydney , Australia.
(11.) Haseeb Shah, Johannes Villmow, Adrian Ulges, Ulrich Schwanecke, Faisal Shafait , " An Open-World Extension to Knowledge Graph Completion Models.", Proceedings of the AAAI 2019, Jan, 2019, Hawai , USA.
(12.) Farrukh Kamran, Muhammad Shahzad, Faisal Shafait , , " Automated Military Vehicle Detection From Low-Altitude Aerial Images", Proceedings of the The International Conference on Digital Image Computing: Techniques and Applications (DICTA), Dec, 2018, Canberra, , Australia.
(13.) Khurram Javed, Faisal Shafait , , " Incremental Learning for Recognition of Cursive Urdu Script using LSTM", Proceedings of the 14th Asian Conference on Computer Vision (ACCV), Dec, 2018, Perth, , Australia.
(14.) Saman Arif, Faisal Shafait , , "Table Detection in Document Images using Foreground and Background Features", Proceedings of the The International Conference on Digital Image Computing: Techniques and Applications (DICTA), Dec, 2018, Canberra, , Australia.
(15.) Nosheen Abid, Adnan Ul Hassan, Faisal Shafait , , "DeepParse: Trainable Postal Address Parser", Proceedings of the The International Conference on Digital Image Computing: Techniques and Applications (DICTA), Dec, 2018, Canberra , Australia.
(16.) Sami-Ur-Rehman, Burhan Ul Tayyab, Muhammad Ferjad Naeem, Adnan Ul-Hasan and Faisal Shafait , , " A Multi-Faceted OCR Framework for Artificial Urdu News Ticker Text Recognition", Proceedings of the 13th IAPR International Workshop on Document Analysis Systems, (DAS), Apr, 2018, Edinburgh, Scotland, , United Kingdom.
(17.) Muhammad Jaleed Khan, Adeel Yousaf, Khurram Khurshid, Asad Abbas, Faisal Shafait , , " Automated Forgery Detection in Multispectral Document Images Using Fuzzy Clustering", Proceedings of the 13th IAPR International Workshop on Document Analysis Systems (DAS), Apr, 2018, Edinburgh, Scotland, , United Kingdom.
(18.) Aman Irshad , Anam Ahmad Khan, Ibrar Yunus, Faisal Shafait , "Real-Time Lane Departure Warning System on a Lower Resource Platform", Proceedings of the Digital Image Computing: Techniques and Applications (DICTA), Dec, 2017, Sydney, NSW , Australia.
(19.) Tayyaba Naz , Anam Ahmad Khan, Faisal Shafait , "Ubiquitous Document Capturing with Deep Learning", Proceedings of the Digital Image Computing: Techniques and Applications (DICTA), Dec, 2017, Sydney, NSW , Australia.
(20.) Azka Gillani , Shah Rukh Qasim, Imran Malik, Faisal Shafait , "Table Detection using Deep Learning", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Nov, 2017, Kyoto , Japan.
(21.) Khurram Javed, Faisal Shafait , , "Real-time Document Localization in Natural Images by Recursive Application of a CNN", Proceedings of the ICDAR2017, Nov, 2017, Kyoto , Japan.
(22.) Asad Abbas, Khurram Khurshid, Faisal Shafait , , "Towards Automated Ink Mismatch Detection in Hyperspectral Document Images", Proceedings of the ICDAR2017, Nov, 2017, Kyoto , Japan.
(23.) Muhammad Ferjad Naeem, Noor ul Sehr Zia, Aqsa Ahmed Awan, Faisal Shafait, Adnan ul Hasan , , "Impact of Ligature Coverage on Training Practical Urdu OCR Systems", Proceedings of the ICDAR2017, Nov, 2017, Kyoto , Japan.
(24.) Hasan F. M. Zaki , Faisal Shafait, Ajmal S. Mian , "Modeling Sub-Event Dynamics in First-Person Action Recognition", Proceedings of the Computer Vision and Pattern Recognition (CVPR) 2017, Nov, 2017, Honolulu, HI , United States.
(25.) Junaid Younas , Muhammad Zeshan Afzal, Muhammad Imran Malik, Faisal Shafait, Paul Lukowicz, Sheraz Ahmed , " D-StaR: A Generic Method for Stamp Segmentation from Document Images", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR) , Oct, 2017, Kyoto , Japan.
(26.) Hasan F. M. Zaki, Faisal Shafait, Ajmal Mian , , "“Modeling 2D Appearance Evolution for 3D Object Categorization", Proceedings of the 18th Int. Conf. on Digital Image Computing: Techniques and Applications, DICTA, Nov, 2016, Gold Coast , Australia.
(27.) Umair Muneer Butt, Muhammad Imran Malik, Sheraz Ahmad, Faisal Shafait, Christian Nansen, Ajmal Saeed Mian , , "Automatic Signature Segmentation Using Hyper-spectral Imaging", Proceedings of the Internationl Conference on Frontiers in Handwriting Recognition (ICFHR), Oct, 2016, Shenzen , China.
(28.) Naveed Akhtar , Faisal Shafait, Ajmal Mian , "Hierarchical Beta Process with Gaussian Process Prior for Hyperspectral Image Super Resolution", Proceedings of the European Conference on Computer Vision ECCV 2016, Sep, 2016, Amsterdam , Netherlands.
(29.) Hasan F. M. Zaki, Faisal Shafait, Ajmal Mian , , "Convolutional Hypercube Pyramid for Accurate RGB-D Object Category and Instance Recognition", Proceedings of the International Conference on Robotics and Automation ICRA, May, 2016, Stockholm , Sweden.
(30.) Fallak Asad , Adnan Ul-Hasan, Faisal Shafait, Andreas Dengel , "High Performance OCR for Camera-Captured Blurred Documents with LSTM Networks", Proceedings of the International Workshop on Document Analysis Systems (DAS), Apr, 2016, Santorini , Greece.
(31.) Hasan F. M. Zaki, Faisal Shafait, Ajmal Mian , , "Localized Deep Extreme Learning Machines for Efficient RGB-D Object Recognition", Proceedings of the 17th Int. Conf. on Digital Image Computing: Techniques and Applications, DICTA, Nov, 2015, Adelaide , Australia.
(32.) Zhipei Luo, Faisal Shafait, Ajmal Mian, , , "Localized Forgery Detection in Hyperspectral Document Images", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Aug, 2015, Sfax , Tunisia.
(33.) Adnan Ul-Hasan, Faisal Shafait ,Marcus Liwicki, , , "Curriculum Learning for Printed Text Line Recognition of Ligature-based Scripts", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Aug, 2015, Sfax , Tunisia.
(34.) Adnan Ul-Hasan, Muhammad Zeshan Afzal, Faisal Shafait, Marcus Liwicki ,Thomas Breuel, , , "A Sequence Learning Approach for Multiple Scripts Identification", Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Aug, 2015, Sfax , Tunisia.
(35.) Faisal Shafait , Muhammad Zeshan Afzal, Joan Pastor-Pellicer, Thomas Breuel, Andreas Dengel, Marcus Liwicki , "Document Image Binarization using LSTM: A Sequence Learning Approach", Proceedings of the 3rd Int Workshop on Historical Document Imaging and Processing, Aug, 2015, Nancy , France.
(36.) Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghoshl, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, Faisal Shafait, Seiichi Uchida, Ernest Valvenyl , , "ICDAR 2015 Competition on Robust Reading", Proceedings of the 13th Int. Conf. on Document Analysis and Recognition, ICDAR, Aug, 2015, Nancy , France.
(37.) Naveed Akhtar, Faisal Shafait,Ajmal Mian, , , "Sparse Bayesian Sparse Representation for Hyperspectral Image Super Resolution", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), Jun, 2015, Boston, Massachusetts , United States.
(38.) Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian, , , "Shape-based Automatic Detection of a Large Number of 3D Facial Landmarks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ( CVPR’15), Jun, 2015, Boston, Massachusetts , United States.
(39.) Dimosthenis Karatzas , Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghoshl, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, Faisal Shafait, Seiichi Uchida, Ernest Valvenyl , "ICDAR 2015 Competition on Robust Reading", Proceedings of the 13th International Conference on Document Analysis and Recognition (ICDAR), Jan, 2015, Nancy , France.
(40.) Hasan F. M. Zaki , Faisal Shafait, Ajmal Mian , "Localized Deep Extreme Learning Machines for Efficient RGB-D Object Recognition", Proceedings of the DICTA 2015, Jan, 2015, Adelaide , Australia.
(41.) Zohaib Khan, Faisal Shafait, Ajmal Mian, , , "Adaptive Spectral Reflectance Recovery using Spatio-Spectral Support from Hyperspectral Images", Proceedings of the 21st Int. Conf. on Image Processing( ICIP’13), Oct, 2014, Paris , France.
(42.) Naveed Akhtar, Faisal Shafait, Ajmal Mian, , , "Sparse Spatio-Spectral Representation for Hyperspectral Image Super-Resolution", Proceedings of the 13th IEEE European Conf. on Computer Vision (ECCV’14), Sep, 2014, Zurich , Switzerland.
(43.) Naveed Akhtar, Faisal Shafait,Ajmal Mian, , , "SUnGP: A greedy sparse approximation algorithm for hyperspectral unmixing", Proceedings of the 22nd Int. Conf. on Pattern Recognition (ICPR’14), Aug, 2014, Stockholm , Sweden.
(44.) Amr Ahmed, Faisal Shafait, , , "Forgery Detection Based on Intrinsic Document Contents", Proceedings of the 11th IAPR Workshop on Document Analysis Systems (DAS’14), Apr, 2014, Tours , France.
(45.) Sara Elkasrawi, Faisal Shafait, , , "Printer Identification using Supervised Learning for Document Forgery Detection", Proceedings of the 11th IAPR Workshop on Document Analysis Systems (DAS’14), Apr, 2014, Tours , France.
(46.) Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian, , , "Gradient based Efficient Feature Selection", Proceedings of the IEEE Winter Conf. on Applications of Computer Vision(WACV’14), Mar, 2014, Colorado , United States.
(47.) Naveed Akhtar, Faisal Shafait, Ajmal Mian, , , "Repeated Constrained Sparse Coding with Partial Dictionaries for Hyperspectral Unmixing", Proceedings of the IEEE Winter Conf. on Applications of Computer Vision(WACV’14), Mar, 2014, Colorado , United States.
(48.) Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian, , , "Biologically significant facial landmarks: How significant are they for gender classification?", Proceedings of the 15th Int. Conf. on Digital Image Computing: Techniques and Applications(DICTA'13), Nov, 2013, Hobart , Australia.
(49.) Christian Schulze, Robby Frister, Faisal Shafait, , , "Eye-tracker based part-image selection for Image Retrieval", Proceedings of the 20th Int. Conf. on Image Processing(ICIP'13), Sep, 2013, Melbourne , Australia.
(50.) Johann Gebhardt, Markus Goldstein, Faisal Shafait, Andreas Dengel, , , "Document Authentication Using Printing Technique Features and Unsupervised Anomaly Detection", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition(ICDAR’13), Aug, 2013, Washington DC , United States.
(51.) Thomas M. Breuel, Adnan Ul-Hasan, Mayce Al Azawi,Faisal Shafait, , , "High-Performance OCR for Printed English and Fraktur Using LSTM Networks", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition( ICDAR’13), Aug, 2013, Washington DC , United States.
(52.) Sheraz Ahmed, Faisal Shafait, Marcus Liwicki, Andreas Dengel, , , "A Generic Method for Stamp Segmentation Using Part-Based Features", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition(ICDAR’13), Aug, 2013, Washington DC , United States.
(53.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Towards Generic Text-Line Extraction", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition( ICDAR’13), Aug, 2013, Washington DC , United States.
(54.) Zohaib Khan, Faisal Shafait, Ajmal Mian, , , "Hyperspectral Imaging for Ink Mismatch Detection", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition( ICDAR’13), Aug, 2013, Washington DC , United States.
(55.) Salman H. Khan, Zeashan Khan, Faisal Shafait, , , "Can Signature Biometrics Address Both Identification and Verification Problems?", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition(ICDAR’13), Aug, 2013, Washington DC , United States.
(56.) Adnan Ul Hasan, Saad Bin Ahmed, Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition( ICDAR’13), Aug, 2013, Washington DC , United States.
(57.) Dimosthenis Karatzas, Faisal Shafait, Seiichi Uchida, Masakazu Iwamura, Lluis Gomez i Bigorda, Sergi Robles Mestre, Joan Mas, David Fernandez Mota, Jon Almaz n Almaz, Lluis Pere de las Heras, , , "ICDAR 2013 Robust Reading Competition", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition(ICDAR’13), Aug, 2013, Washington DC , United States.
(58.) Akram El-Korashy ,Faisal Shafait, , , "Search Space Reduction for Holistic Ligature Recognition in Urdu Nastalique Script ", Proceedings of the 12th Int. Conf. on Document Analysis and Recognition(ICDAR’13), Aug, 2013, Washington DC , United States.
(59.) Renwu Gao, Faisal Shafait, Seiichi Uchida, Yaokai Feng, , , "A Hierarchical Visual Saliency Model for Character Detection in Natural Scenes", Proceedings of the 5th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’13), Aug, 2013, Washington DC , United States.
(60.) Muhammad Zeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Mohammad Reza Yousefi, Faisal Shafait, homas M. Breuel, , , "Robust Binarization of Stereo and Monocular Document Images Using Percentile Filter", Proceedings of the 5th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’13), Aug, 2013, Washington DC , United States.
(61.) Mark R. Shortis, Mehdi Ravanbakskh, Faisal Shafait, Euan S. Harvey, Ajmal Mian, James W. Seager, Philip Culverhouse, Danelle Cline, Duane Edgington, , , "“A review of techniques for the identification and measurement of fish in underwater stereo-video image sequences", Proceedings of the SPIE Videometrics, Range Imaging, and Applications XII, May, 2013, Munich , Germany.
(62.) Nazly Sabbour, Faisal Shafait, , , "A segmentation-free approach to Arabic and Urdu OCR", Proceedings of the SPIE Document Recognition and Retrieval XX( DRR’13), Feb, 2013, San Francisco , United States.
(63.) Adnan Ul-Hasan, Syed Saqib Bukhari, Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "Semi-Automated OCR Database Generation for Nabataean Scripts", Proceedings of the 21st Int. Conf. on Pattern Recognition (ICPR’12), Nov, 2012, Tsukuba , Japan.
(64.) Hasan S. M. Al-Khaffaf, Faisal Shafait, Michael Cutter, Thomas M. Breuel, , , "On the Performance of Decapod's Digital Font Reconstruction", Proceedings of the 21st Int. Conf. on Pattern Recognition (ICPR’12), Nov, 2012, Tsukuba , Japan.
(65.) Muhammad Zeshan Afzal, Syed Saqib Bukhari, Martin Krämer, Faisal Shafait, Thomas M. Breuel, , , "Robust Stereo Matching for Document Images Using Parameter Selection of Text-Line Extraction", Proceedings of the 21st Int. Conf. on Pattern Recognition (ICPR’12), Nov, 2012, Tsukuba , Japan.
(66.) Martin Krämer, Muhammad Zeshan Afzal, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Robust Stereo Correspondence for Documents by Matching Connected Components of Text-Lines with Dynamic Programming", Proceedings of the 21st Int. Conf. on Pattern Recognition (ICPR’12), Nov, 2012, Tsukuba , Japan.
(67.) Joost Van Beusekom, Armin Stahl, Faisal Shafait, , , "“Lessons Learned from Automatic Forgery Detection in over 100,000 Invoices", Proceedings of the 5th Int. Workshop on Computational Forensics(IWCF’12), Nov, 2012, Tsukuba , Japan.
(68.) Barbora Micenkova, Joost Van Beusekom, Faisal Shafait, , , "Stamp Verification for Automated Document Authentication", Proceedings of the 5th Int. Workshop on Computational Forensics(IWCF’12), Nov, 2012, Tsukuba , Japan.
(69.) Asif Shahab, Faisal Shafait, Andreas Dengel, Seiichi Uchida, , , "How Salient is Scene Text?", Proceedings of the 10th IAPR Workshop on Document Analysis Systems(DAS’12), Mar, 2012, Gold Coast , Australia.
(70.) Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "Scanning Neural Network for Text Line Recognition", Proceedings of the 10th IAPR Workshop on Document Analysis Systems(DAS’12), Mar, 2012, Gold Coast , Australia.
(71.) Adnan Ul Hasan, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "OCR-Free Table of Contents Detection in Urdu Books", Proceedings of the 10th IAPR Workshop on Document Analysis Systems(DAS’12), Mar, 2012, Gold Coast , Australia.
(72.) Muhammed Zeeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Improvements to Uncalibrated Feature-based Stereo Matching for Document Images by using Text-Line Segmentation", Proceedings of the 10th IAPR Workshop on Document Analysis Systems(DAS’12), Mar, 2012, Gold Coast , Australia.
(73.) Takumi Toyama, Thomas Kieninger, Faisal Shafait, Andreas Dengel, , , "Gaze Guided Object Recognition Using a Head-Mounted Eye Tracker", Proceedings of the 7th Int. Symposium on Eye Tracking Research and Applications (ETRA’12), Mar, 2012, Santa Barbara , United States.
(74.) Takuya Kobayashi, Takumi Toyama, Faisal Shafait, Andreas Dengel, Masakazu Iwamura, Koichi Kise, , , "Recognizing Words in Scenes with a Head-Mounted Eye-Tracker", Proceedings of the 10th IAPR Workshop on Document Analysis Systems(DAS’12), Feb, 2012, Gold Coast , Australia.
(75.) Matthias Reif, Faisal Shafait, Andreas Dengel, , , "“Prediction of Classifier Training Time including Parameter Optimization", Proceedings of the 34th Annual German Conference on Artificial Intelligence(KI’11), Oct, 2011, Berlin , Germany.
(76.) Asif Shahab, Faisal Shafait, Andreas Dengel, , , "“ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition (ICDAR’11), Sep, 2011, Beijing , China.
(77.) Asif Shahab, Faisal Shafait, Andreas Dengel, , , "Bayesian Approach to Photo Time-Stamp Recognition", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition(ICDAR’11), Sep, 2011, Beijing , China.
(78.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Text-Line Extraction using a Convolution of Isotropic Gaussian Filter with a Set of Line Filters", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition (ICDAR’11), Sep, 2011, Beijing , China.
(79.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "High Performance Layout Analysis of Arabic and Urdu Document Images", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition(ICDAR’11), Sep, 2011, Beijing , China.
(80.) Joost Van Beusekom, Faisal Shafait, , , "Distortion Measurement for Automatic Document Verification", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition(ICDAR’11), Sep, 2011, Beijing , China.
(81.) Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "An evaluation of HMM-based Techniques for the Recognition of Screen Rendered Text", Proceedings of the 11th Int. Conf. on Document Analysis and Recognition(ICDAR’11), Sep, 2011, Beijing , China.
(82.) Faisal Shafait, Michael P. Cutter, Joost van Beusekom, Syed Saqib Bukhari, Thomas M. Breuel, , , "Decapod: A flexible, low cost digitization solution for small and medium archives", Proceedings of the 4th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’11), Sep, 2011, Beijing , China.
(83.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Border Noise Removal of Camera-Captured Document Images using Page-Frame Detection", Proceedings of the 4th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’11), Sep, 2011, Beijing , China.
(84.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "An Image Based Performance Evaluation Method for Page Dewarping Algorithms using SIFT Features", Proceedings of the 4th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’11), Sep, 2011, Beijing , China.
(85.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "The IUPR Dataset of Camera-Captured Document Images", Proceedings of the 4th Int. Workshop on Camera-Based Document Analysis and Recognition(CBDAR’11), Sep, 2011, Beijing , China.
(86.) Takumi Toyama, Thomas Kieninger, Faisal Shafait, Andreas Dengel, , , "Museum Guide 2.0 - An Eye-Tracking based Personal Assistant for Museums and Exhibits", Proceedings of the Int. Conf. on Re-Thinking Technology in Museums, May, 2011, Limerick , Ireland.
(87.) Michael P. Cutter, Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Font group identification using reconstructed fonts", Proceedings of the SPIE Document Recognition and Retrieval XVIII (DRR’11), Jan, 2011, San Francisco , United States.
(88.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Improved document image segmentation algorithm using multiresolution morphology", Proceedings of the SPIE Document Recognition and Retrieval XVIII (DRR’11), Jan, 2011, San Francisco , United States.
(89.) Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "Discriminative Learning for Script Recognition", Proceedings of the 17th Int. Conf. on Image Processing, (ICIP’10), Sep, 2010, Hong Kong , China.
(90.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Performance Evaluation of Curled Textlines Segmentation Algorithms on CBDAR 2007 Dewarping Contest Dataset", Proceedings of the 17th Int. Conf. on Image Processing, (ICIP’10), Sep, 2010, Hong Kong , China.
(91.) Michael P. Cutter, Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Unsupervised Font Reconstruction Based on Token Co-occurrence", Proceedings of the 10th ACM Symposium on Document Engineering,(DocEng’10), Sep, 2010, Manchester , United Kingdom.
(92.) Faisal Shafait, Matthias Reif, Christian Kofler, Thomas M. Breuel, , , "Pattern Recognition Engineering", Proceedings of the RapidMiner Community Meeting and Conference,(RCOMM’10), Sep, 2010, Dortmund , Germany.
(93.) Sarah Daniel Abdelmessih, Faisal Shafait, Matthias Reif, Markus Goldstein, , , "Landmarking for Meta-Learning using RapidMiner", Proceedings of the RapidMiner Community Meeting and Conference,(RCOMM’10), Sep, 2010, Dortmund , Germany.
(94.) Alexander Arimond, Christian Kofler, Faisal Shafait , , "Distributed Pattern Recognition in RapidMiner", Proceedings of the RapidMiner Community Meeting and Conference,(RCOMM’10), Sep, 2010, Dortmund , Germany.
(95.) Faisal Shafait, Ray Smith, , , "Table Detection in Heterogeneous Documents", Proceedings of the 9th IAPR Workshop on Document Analysis Systems (DAS’10), Jun, 2010, Boston , United States.
(96.) Asif Shahab, Faisal Shafait, Thomas Kieninger, Andreas Dengel, , , "An Open Approach towards the Benchmarking of Table Structure Recognition Systems", Proceedings of the 9th IAPR Workshop on Document Analysis Systems, (DAS’10), Jun, 2010, Boston , United States.
(97.) Syed Saqib Bukhari, Mayce Ibrahim Ali Al-Azawi, Faisal Shafait, Thomas M. Breuel, , , "Document Image Segmentation using Discriminative Learning over Connected Components", Proceedings of the 9th IAPR Workshop on Document Analysis Systems, (DAS’10), Jun, 2010, Boston , United States.
(98.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Document Inspection Using Text-Line Alignment", Proceedings of the 9th IAPR Workshop on Document Analysis Systems,DAS’10, Jun, 2010, Boston , United States.
(99.) Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel, , , "Connected Component level Multiscript Identification from Ancient Document Images", Proceedings of the 9th IAPR Workshop on Document Analysis Systems, DAS’10, Jun, 2010, Boston , United States.
(100.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Performance Evaluation of Curled Textlines Segmentation Algorithms", Proceedings of the 9th IAPR Workshop on Document Analysis Systems,DAS’10, Jun, 2010, Boston , United States.
(101.) Thomas M. Breuel, Faisal Shafait, , , " AutoMLP: Simple, Effective, Fully Automated Learning Rate and Size Adjustment", Proceedings of the The Learning Workshop, Apr, 2010, Snowbird,Utah , United States.
(102.) Emanuel Indermühle, Horst Bunke, Faisal Shafait, Thomas M. Breuel , , "Text versus non-Text Distinction in Online Handwritten Documents", Proceedings of the 25th ACM Symposium On Applied Computing,Document Engineering Track,SAC’10 , Mar, 2010, Sierre , Switzerland.
(103.) Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel , , "Visual Recognition of Permuted Words", Proceedings of the SPIE Human Vision and Electronic Imaging XV,HVEI’10., Jan, 2010, San Jose , United States.
(104.) Faisal Shafait, Thomas M. Breuel, , , "A Simple and Effective Approach for Border Noise Removal from Document Images", Proceedings of the 13th IEEE Int. Multi-topic Conference,INMIC’09, Dec, 2009, Islamabad , Pakistan.
(105.) Sheikh Faisal Rashid, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel , , "A Discriminative Learning Approach for Orientation Detection of Urdu Document Images", Proceedings of the 13th IEEE Int. Multi-topic Conference, Dec, 2009, INMIC’09 , Pakistan.
(106.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Curled Textline Information Extraction from Grayscale Camera-Captured Document Images", Proceedings of the 16th Int. Conf. on Image Processing, ICIP’09, Nov, 2009, Cairo , Egypt.
(107.) Yves Rangoni, Faisal Shafait, Joost van Beusekom, Thomas M. Breuel, , , "Recognition Driven Page Orientation Detection", Proceedings of the 16th Int. Conf. on Image Processing,ICIP’09. , Nov, 2009, Cairo , Egypt.
(108.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Ridges Based Curled Textline Region Detection from Grayscale Camera-Captured Document Images", Proceedings of the 13th Int. Conf. on Computer Analysis of Images and Patterns,CAIP’09, Sep, 2009, Münster , Germany.
(109.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Automatic Line Orientation Measurement for Questioned Document Examination", Proceedings of the 3rd Int. Workshop on Computational Forensics,IWCF’09, Aug, 2009, Hague , Netherlands.
(110.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Dewarping of Document Images using Coupled-Snakes", Proceedings of the 3rd Int. Workshop on Camera-Based Document Analysis and Recognition,CBDAR’09, Jul, 2009, Barcelona , Spain.
(111.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Foreground-Background Regions Guided Binarization of Camera-Captured Document Images", Proceedings of the 3rd Int. Workshop on Camera-Based Document Analysis and Recognition,CBDAR’09, Jul, 2009, Barcelona , Spain.
(112.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Script-Independent Handwritten Textlines Segmentation using Active Contours", Proceedings of the 10th Int. Conf. on Document Analysis and Recognition, ICDAR’09, Jul, 2009, Barcelona , Spain.
(113.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Coupled Snakelet Model for Curled Textline Segmentation of Camera-Captured Document Images", Proceedings of the 10th Int. Conf. on Document Analysis and Recognition, ICDAR’09. , Jul, 2009, Barcelona , Spain.
(114.) Yves Rangoni, Faisal Shafait, Thomas M. Breuel, , , "OCR Based Thresholding", Proceedings of the 11th IAPR Conf. on Machine Vision Applications, MVA’09,, May, 2009, Yokohama , Japan.
(115.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Resolution Independent Skew and Orientation Detection for Document Images", Proceedings of the SPIE Document Recognition and Retrieval XVI,DRR’09, Jan, 2009, San Jose , United States.
(116.) Faisal Shafait, Joost van Beusekom, Daniel Keysers, Thomas M. Breuel, , , "Background Variability Modeling for Statistical Layout Analysis", Proceedings of the 19th Int. Conf. on Pattern Recognition, ICPR’08, Dec, 2008, Tampa, Florida , United States.
(117.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Automated OCR Ground Truth Generation", Proceedings of the 8th IAPR Workshop on Document Analysis Systems, DAS’08. , Sep, 2008, Nara , Japan.
(118.) Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel, , , "Segmentation of Curled Text Lines using Active Contours", Proceedings of the 8th IAPR Workshop on Document Analysis Systems, DAS’08, Sep, 2008, Nara , Japan.
(119.) Faisal Shafait, Joost van Beusekom, Daniel Keysers, Thomas M. Breuel, , , "Structural Mixtures for Statistical Layout Analysis", Proceedings of the 8th IAPR Workshop on Document Analysis Systems,DAS’08, Sep, 2008, Nara , Japan.
(120.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , "Document Signatures Using Intrinsic Features for Counterfeit Detection", Proceedings of the 2nd Int. Workshop on Computational Forensics,,IWCF’08, Aug, 2008, Washington DC , United States.
(121.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , "Efficient Implementation of Local Adaptive Thresholding Techniques Using Integral Images", Proceedings of the SPIE Document Recognition and Retrieval XV,DRR’08, Jan, 2008, San Jose , United States.
(122.) Faisal Shafait ,Thomas M. Breuel, , , "Document Image Dewarping Contest", Proceedings of the 2nd Int. Workshop on Camera-Based Document Analysis and Recognition,CBDAR’07, , Sep, 2007, , Brazil.
(123.) Joost van Beusekom, Daniel Keysers, Faisal Shafait, Thomas M. Breuel, , , "Example-Based Logical Labeling of Document Title Page Images", Proceedings of the 9th Int. Conf. on Document Analysis and Recognition,ICDAR’07, Sep, 2007, Curitiba , Brazil.
(124.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , "GREC 2007 Arc Segmentation Contest: Evaluation of Four Participating Algorithms", Proceedings of the In Graphics Recognition: Recent Advances and New Opportunities ,GREC'07, Sep, 2007, Curitiba , Brazil.
(125.) Joost van Beusekom, Faisal Shafait, Thomas M. Breuel, , , " Image-Matching for Revision Detection in Printed Historical Documents", Proceedings of the 29th Annual Symposium of the German Association for Pattern Recognition,DAGM’07, Sep, 2007, Heidelberg , Germany.
(126.) Faisal Shafait, Joost van Beusekom, Daniel Keysers, Thomas M. Breuel, , , "Page Frame Detection for Marginal Noise Removal from Scanned Documents", Proceedings of the 15th Scandinavian Conference on Image Analysis,SCIA’07, Jun, 2007, Aalborg , Denmark.
(127.) Daniel Keysers, Faisal Shafait, Thomas M. Breuel, , , " Document Image Zone Classification - A Simple High-Performance Approach", Proceedings of the 2nd Int. Conf. on Computer Vision Theory and Applications, VISAPP’07, Mar, 2007, Barcelona , Spain.
(128.) Faisal Shafait, Adnan-ul-Hasan, Daniel Keysers, Thomas M. Breuel, , , "Layout Analysis of Urdu Document Images", Proceedings of the 10th IEEE Int. Multi-topic Conference, INMIC’06, Dec, 2006, Islamabad , Pakistan.
(129.) Faisal Shafait, Ralph Kricke, Islam Shdaifat, Rolf-Rainer Grigat, , , "Real Time Lip Motion Analysis for a Person Authentication System Using Near Infrared Illumination", Proceedings of the 13th Int. Conf. on Image Processing,ICIP’06, Oct, 2006, Atlanta , United States.
(130.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , " Pixel-Accurate Representation and Evaluation of Page Segmentation in Document Images", Proceedings of the 18th Int. Conf. on Pattern Recognition,ICPR’06, Aug, 2006, Hong Kong , China.
(131.) Joost van Beusekom, Daniel Keysers, Faisal Shafait, Thomas M. Breuel, , , "Distance Measures for Layout-Based Document Image Retrieval", Proceedings of the 2nd IEEE Int. Conf. on Document Image Analysis for Libraries, DIAL’06, Apr, 2006, Lyon , France.
(132.) Waqar Zia ,Faisal Shafait , , "Reduced Complexity Techniques for Long-Term Memory Motion Compensated Prediction in Hybrid Video Coding", Proceedings of the 25th Picture Coding Symposium, PCS’06, Apr, 2006, Beijing , China.
(133.) Faisal Shafait, Daniel Keysers, Thomas M. Breuel, , , " Performance Comparison of Six Algorithms for Page Segmentation", Proceedings of the 7th IAPR Workshop on Document Analysis Systems,DAS’06, Feb, 2006, Nelson , New Zealand.
(134.) Faisal Shafait, Muhammad Usman, Adnan-ul-hasan, Habibullah Jamal, Shoab A. Khan, , , "An Architecture of 2-D IDCT for Real Time Decoding of MPEG/JPEG compliant bitstreams", Proceedings of the 17th IEEE Int. Conf. on Micro-electronics, ICM’05, Dec, 2005, Islamabad , Pakistan.
(135.) Faisal Shafait, Marco Grimm, Rolf-Rainer Grigat, , , " Low-Complexity Camera Ego-Motion Estimation Algorithm for Real Time Applications", Proceedings of the 8th IEEE Int. Multitopic Conference,INMIC’04, Dec, 2004, Lahore , Pakistan.
(136.) Faisal Shafait, Muhammad Saleem Pervez, Arish Asif Qazi, Jörg Wollnack, Thomas Trittin, , , "Real Time Two-Step Inspection System for Assembled Valve Keys in Automobile Cylinder Heads", Proceedings of the 3rd Int. Conf. on Image and Graphics, ICIG’04, Dec, 2004, Hong Kong , China.
(137.) Habibullah Jamal ,Faisal Shafait , , "An Efficient Architecture for Displaying JPEG images in Cell Phones", Proceedings of the MMU Int. Symp. on Information and Communication Technologies,M2USIC’04, Oct, 2004, Putrajaya , Malaysia.
(138.) Faisal Shafait, Marco Grimm, Rolf-Rainer Grigat, , , "Evaluation of a Vision-Based 2-Button Remote Control for Interactive Television", Proceedings of the Proc. 11th IEEE Int. Workshop on Signals, Systems, and Image Processing,IWSSIP’04, Sep, 2004, Poznan , Poland.
(139.) Muhammad Saleem Pervez ,Faisal Shafait , , "Real Time Inspection of Assembled Valve Keys in Cylinder Heads using CCD Cameras", Proceedings of the IEEE E-Tech’04, Jul, 2004, Karachi , Pakistan.
(140.) Muhammad Saleem Pervez ,Faisal Shafait , , "Real Time Inspection of Assembled Valve Keys in Cylinder Heads using CCD Cameras", Proceedings of the IEEE E-Tech’04, Jul, 2004, Karachi , Pakistan.
(141.) Faisal Shafait, Syed Muhammad Imran, Sven Klette-Matzat , , "Fault Detection and Localization in Empty Water Bottles through Machine Vision", Proceedings of the IEEE E-Tech’04, Jul, 2004, Karachi , Pakistan.

Assistant Professor , The University of Western Australia, Perth, Australia
January 2013 - January 2015


Adjunct Lecturer , Technische Universität Kaiserslautern (TUKL), Germany
April 2009 - October 2012



Senior Researcher , German Research Center for Artificial Intelligence (DFKI)
November 2009 - January 2013


Postdoctoral Researcher , Google Inc, Mountain View, CA, USA
November 2008 - March 2009