Rashik Shadman
Department of Electrical and Computer Engineering
Clarkson University, Potsdam, NY 13699, USA
Abstract: Biometric authentication has become one of the most widely used tools in the current technological era to authenticate users and to distinguish between genuine users and imposters. Face and fingerprint are common forms of biometrics modalities that have proven very effective. Deep learning-based face and fingerprint recognition systems are now commonly used across different applications. However, these systems usually operate like black-box models that do not provide necessary explanations for their decisions. This is a major disadvantage due to which users cannot trust such Artificial Intelligence-based biometric systems.This talk addresses this problem by applying a new method for explainable face and fingerprint recognition systems. We use a Class Activation Mapping (CAM) based discriminative localization (very narrow/specific localization) technique called Scaled Directed Divergence (SDD) to visually explain the results of deep learning-based face and fingerprint recognition systems. We perform fine localization of relevant face and fingerprint features. The provided visual explanations with narrow localization of relevant features can ensure much-needed transparency and trust for deep learning-based face and fingerprint recognition systems.
BIO: Rashik Shadman received his B.S. degree in Electrical and Electronic Engineering from Islamic University of Technology, Bangladesh, and his M.S. degree in Electrical and Computer Engineering from Southern Illinois University Carbondale, IL, USA. He is currently pursuing a Ph.D. in Electrical and Computer Engineering at Clarkson University, Potsdam, NY. His research focuses on deep learning-based biometric systems, explainable AI, keystroke dynamics.
Tuesday, February 4, 2025, 12:30-1:30 pm, CAMP 194
Join Link: https://clarkson.zoom.us/j/94088483647?pwd=2bmoDHPYozdIWgj1SrdVbqQaQUMUiz.1
*Co-Sponsored by IEEE student branch and HKN