Saad B. Ahmed is an Assistant Professor in the Computer Science Department at Lakehead University, Thunder Bay, Canada. He had served as a postdoctoral associate at University of Western Ontario, London. He has dedicated his career to the research of image analysis and pattern recognition.
Throughout this academic journey, he has actively contributed to several research initiatives, one of which involved curating a dataset of handwritten Arabic characters for recognition purposes. This project encompassed the acquisition of Arabic scene text images and the subsequent application of machine learning and pattern recognition techniques to conduct research on the gathered samples.
Currently, his research endeavors are primarily centered on the domains of hyperspectral image analysis and the role of explainable AI in medical image analysis (MRI, CT Scan, Positron emission tomography (PET)), exploiting the role of deep learning in initial diagnosis, indigenous text analysis and eutrophication analysis using deep learning approaches.
His efforts have yielded over 50 publications cited in top-tier journals and conferences within the realm of medical image analysis. His research stands in advancing early diagnosis within the medical field. Furthermore, he has forged partnerships with industry to conduct collaborative projects with renowned Universities worldwide.
Our Projects & Publications
Our Research
We focus our research in all aspects of Data science. Click to explore.
Our Team Members
Latest News
- 3rd International Conference On Advanced Engineering, Technology And Applications
May 24-25, 2024
University Of Catania, Italy
- Our Research Published in Sensors
Hyperspectral data analysis is being utilized as an effective and compelling tool for image processing,
providing unprecedented levels of information and insights for various applications. In this manuscript, we
have compiled and presented a comprehensive overview of recent advances in hyperspectral data
analysis that can provide assistance for the development of customized techniques for hyperspectral
document images. We review the fundamental concepts of hyperspectral imaging, discuss various
techniques for data acquisition, and examine state-of-the-art approaches to the preprocessing, feature
extraction, and classification of hyperspectral data by taking into consideration the complexities of
document images. We also explore the possibility of utilizing hyperspectral imaging for addressing critical
challenges in document analysis, including document forgery, ink age estimation, and text extraction from
degraded or damaged documents.
- Our Research Published in IEEE Access
Hyperspectral Imaging (HSI) uses large portions of the electromagnetic spectrum to obtain information
from images that would be very difficult to get otherwise. An important task in forensic analysis of
documents is to extract signatures for authentication. Signatures in documents often overlap with other
parts of a document such as typed text or stamps and hence it is difficult to retrieve them. In this work we
present a novel algorithm for recovering signatures from hyperspectral images of documents where
signatures overlap typed text, seals, stamps, or other images.
- Two Students from National University of Science and Technology (NUST) joining IAPI-RL on
MITACS Globlink Research Awards.
Latest News
3rd International Conference On Advanced Engineering,
Technology & Applications
24-May-2024 to 25-May-2024
University Of Catania, Italy
Our Research Published In SENSORS
In our work, we review the fundamental concepts of hyperspectral imaging and discuss various techniques for data acquisition. We also examine state-of-the-art approaches to preprocessing, feature extraction, and classification of hyperspectral data, taking into consideration the complexities associated with document images. Furthermore, we explore the potential of utilizing hyperspectral imaging to address critical challenges in document analysis. These challenges include document forgery detection, ink age estimation, and text extraction from degraded or damaged documents.
Research Published in IEEE Access
Hyperspectral Imaging (HSI) uses large portions of the electromagnetic spectrum to obtain information from images that would be very difficult to get otherwise. An important task in forensic analysis of documents is to extract signatures for authentication. Signatures in documents often overlap with other parts of a document such as typed text or stamps, and hence it is difficult to retrieve them. In this work, we present a novel algorithm for recovering signatures from hyperspectral images of documents where signatures overlap typed text, seals, stamps, or other images.
MITACS Globlink Research Awards
Two Students from National University of Science and Technology (NUST) joining Image Analysis & Pattern Identification Research Lab on MITACS Globlink Research Awards.