Biometric Recognition and Identification: A Useful Testbed for Artificial Intelligence

Slides (pdf)  Size: 16.7MB

Abstract

Recent advances in artificial intelligence (AI) are often showcased through innovations like self-driving cars, robotics, large language models, image and video synthesis, 3D modeling, and visualization. While AI demonstrates remarkable potential in these areas, it also reveals vulnerabilities to data and domain shifts, adversarial attacks, bias, as well as issues surrounding privacy and explainability.

In this talk, I will explore how AI-based approaches for biometric recognition and identification exhibit similar weaknesses and introduce methods to mitigate them, at least partially. Specifically, I will present techniques for enhancing body/face/gait recognition and identification across varying ranges and altitudes, adapting from visual to thermal imagery, detecting and reducing bias through adversarial training and knowledge distillation, developing explainable biometric features, and implementing identity encryption.

Biography

Prof. Rama Chellappa is a Bloomberg Distinguished Professor in Computer Vision and Artificial Intelligence in the Departments of Electrical and Computer Engineering (ECE) in the Whiting School of Engineering and Biomedical Engineering in the School of Medicine at Johns Hopkins University (JHU). At Hopkins, he is serving as an interim co-Director of the Data Science and Artificial Intelligence Institute, and is affiliated with CIS, CLSP, IAA and MINDS. He also holds a non-tenured position as a College Park Professor in the ECE department at the University of Maryland. His research interests are in artificial intelligence, computer vision, machine learning and pattern recognition. He received the 2012 K. S. Fu Prize from the International Association of Pattern Recognition (IAPR). He is a recipient of the Society, Technical Achievement, and Meritorious Service Awards from the IEEE Signal Processing Society, the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society and the Inaugural Leadership Award from the IEEE Biometrics Council. He received the 2020 IEEE Jack S. Kilby Medal for Signal Processing, the 2023 IEEE Computer Society Pattern Analysis and Machine Intelligence Distinguished Researcher Award, and the 2024 Edwin H. Land Medal from Optica (formerly Optical Society of America). He is a member of the National Academy of Engineering and a Foreign Fellow of the Indian National Academy of Engineering. He has been recognized as a Distinguished Alumni by the ECE department at Purdue University and the Indian Institute of Science. He is a Fellow of AAAI, AAAS, ACM, AIMBE, IAPR, IEEE, NAI, OSA, and the Washington Academy of Sciences and holds nine patents.

Rama Chellappa
Johns Hopkins University, US