Mohamed Shehata

Papers

Total Citations

309

H-Index

About

Mohamed Shehata is a computer vision researcher whose work centers on image matching, visual tracking, and robust feature extraction for real-world applications. His most influential contribution is a comprehensive 2017 study comparing SIFT, SURF, BRIEF, and ORB algorithms for distorted image matching, which has garnered over 300 citations and become a foundational reference for practitioners in robotics and surveillance. Shehata’s research systematically evaluates these techniques under varying transformations—such as scaling, rotation, and blur—providing critical guidance for selecting the right algorithm in applications like object recognition and 3D reconstruction. He also developed an adaptive framework for robust visual tracking (2018), addressing challenges like occlusion and camera motion, with implications for medical imaging and autonomous systems. By bridging theoretical evaluation with practical deployment, Shehata’s work helps engineers and researchers optimize performance in computationally constrained environments. His citation impact and focus on benchmarking underscore his role in advancing reliable, real-time computer vision solutions.