Remote Face Recognition

Slides (pdf)  Size: 8.82MB

Abstract

Although deep learning approaches for face recognition work well for high-quality images and videos acquired at short ranges, their performance on images and videos collected remotely (500-1000 meters) is unsatisfactory. Remotely acquired faces suffer from degradations due to atmospheric turbulences, blur and low-resolution. In this lecture, I will present a summary of three remote face recognition approaches we have developed since 2008. The first approach was based on using shallow representations derived from sparse dictionaries. The second approach based on deep representations was tuned to multiple-shot videos and surveillance videos with low-quality frames. After detection, association and aggregation, the faces are recognized using an unsupervised subspace learning approach and a subspace-to-subspace similarity metric. I will then discuss the third method that explicitly considers image degradation due to atmospheric turbulence that is common while capturing images at long ranges (300m-1000m). To mitigate the degradations due to turbulence that includes deformation and blur, this method disentangles blur and deformation due to turbulence and reconstructs a restored image. Adversarial and perceptual loss terms are employed to reconstruct a sharp image and suppress the artifacts. Extensive experimental results demonstrating the effectiveness of these three approaches on many challenging face datasets will be presented.

Biography

Rama Chellappa is a Bloomberg Distinguished Professor in the Departments of Electrical and Computer Engineering and Biomedical Engineering at Johns Hopkins University (JHU). At JHU, he is also affiliated with MINDS, CIS and CLSP. He holds a non-tenure position as a College Park Professor in the ECE department at University of Maryland (UMD). Before coming to JHU in August 2020, he was a Distinguished University Professor, a Minta Martin Professor of Engineering, a Professor in the ECE department and the University of Maryland Institute Advanced Computer Studies at UMD. At UMD, he was also affiliated with the Center for Automation Research and the Department of Computer Science. From 1981-1991, he was an assistant and associate professor in the Department of EE-Systems at University of Southern California. He received the B.E. (Hons.) degree in Electronics and Communication Engineering from the University of Madras, India in 1975 and the M.E. (with Distinction) degree from the Indian Institute of Science, Bangalore, India in 1977. He received the M.S.E.E. and Ph.D. Degrees in Electrical Engineering from Purdue University, West Lafayette, IN, in 1978 and 1981 respectively. His current research interests are computer vision, machine learning, artificial intelligence, signal and image/video processing.

Chellappa received an NSF Presidential Young Investigator Award, four IBM Faculty Development Awards, an Excellence in Teaching Award from the School of Engineering at USC, and several paper awards from Biometrics and Pattern Recognition conferences. He is a recipient of the 2020 IEEE Jack S. Kilby Signal Processing Medal. He is also a recipient of the K.S. Fu Prize from the International Association of Pattern Recognition (IAPR). He received the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society. He also received the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society. Recently, he was recognized with the inaugural Leadership Award from the IEEE Biometrics Council. At UMD, he was elected as a Distinguished Faculty Research Fellow, as a Distinguished Scholar-Teacher, received three Outstanding Innovator Awards from the Office of Technology Commercialization, and an Outstanding GEMSTONE Mentor Award from the Honors College. He received the Outstanding Faculty Research Award and the Poole and Kent Teaching Award for Senior Faculty from the College of Engineering. In 2010, he was recognized as an Outstanding ECE by Purdue University. He also received the Distinguished Alumni Award from the Indian Institute of Science in 2016. He is a Fellow of IEEE, IAPR, OSA, AAAS, ACM and AAAI. He holds six patents.

Chellappa served as the Editor-in-Chief of IEEE Transactions on Pattern Analysis and Machine Intelligence. He has served as a General and Technical Program Chair for several IEEE international and national conferences and workshops. He is a Golden Core Member of the IEEE Computer Society and served as a Distinguished Lecturer of the IEEE Signal Processing Society. He served as the inaugural President of the IEEE Biometrics Council.

Rama Chellappa
Johns Hopkins University, US