Face Recognition across Heterogeneous Image Spectrums
Prof Kar-Ann Toh, Yonsei University, South Korea
Co-organized by IEEE Circuits and Systems Singapore Chapter, and
INFINITUS, Centre for Infocomm Technologies |
Abstract
Heterogeneous face recognition refers to identification of persons by means of a comparison across face images acquired from different imaging modalities such as visual and infra-red spectrums. In this talk, we shall walk through the motivation and main challenges in heterogeneous face recognition prior to suggesting a solution to the problem. Specifically, we capitalize on the capability of Gabor filtering for feature extraction across the different modalities. A random projection is subsequently applied to fuse the extracted features allowing tolerance to minor image variations. The entire process is subsequently integrated for computational simplicity. Our empirical evaluation based on public datasets show promising results for the proposal.
Speaker Biography
Kar-Ann Toh is a Professor in the School of Electrical and Electronic Engineering at Yonsei University, South Korea. He received the PhD degree from Nanyang Technological University(NTU), Singapore and worked for two years in the aerospace industry prior to his post-doctoral appointments at research centers in NTU from 1998 to 2002. He was affiliated with Institute for Infocomm Research in Singapore from 2002 to 2005 prior to his current appointment in Korea. His research interests include pattern classification, machine learning and biometrics. He is a co-inventor of a US patent and has made several PCT filings related to biometric applications. Besides being active in publications, Dr. Toh has served as a member of technical program committee and advisory board for international conferences related to biometrics and artificial intelligence. He has also served as an associate editor of IEEE Transactions on Information Forensics and Security, Pattern Recognition Letters and IET Biometrics. He is a senior member of the IEEE.
Back to top |