banner2
new   ***    Program Schedule  ***      ***      Urgent Notice for Registration   ***      ***   Updated list of accepted papers (15/01/2019)  ***   

Invited Speaker


muramatsu Daigo Muramatsu
Institute of Scientific and Industrial Research, Osaka University, Japan
Title: Silhouette-based gait recognition from image sequences with occlusion
Abstract: Gait recognition is a biometric method for person recognition, and it has an advantage that gait feature for recognition can be obtained at a distance. We, therefore, have a chance to recognize a subject in CCTV footage. But in order to realize recognition of subject in CCTV footage, we need to tackle several issues including view difference, speed change, and occlusion. In this talk, we focus on occlusion issue, and propose a technique to reconstruct full-body gait feature from a partial gait feature extracted from a gait image sequence with occlusion; we call this method "gait regeneration". In order to achieve gait regeneration, we employ subspace-based method; and improve accuracy of reconstruction by incorporating a term that measures wellness of gait feature. Incorporation of the gait feature wellness contributes to improve reconstruction accuracy and person recognition accuracy. We report evaluation results on a subset of publicly available gait database named OULP.



Biography: Daigo Muramatsu received the B.S. M.E., and Ph.D. degrees in electrical, electronics, and computer engineering from Waseda University, Tokyo, Japan, in 1997, 1999, and 2006, respectively. He is currently an Associate Professor of The Institute of Scientific and Industrial Research, Osaka University. His current research interests include gait recognition, signature verification, and biometric fusion. He is a member of the IEEE, IEICE, and the IPSJ. He has obtained several honors and awards, including the 2nd Int. Workshop on Biometrics and Forensics (IWBF 2014), IAPR Best Paper Award, and the 9th IAPR Int. Conf. on Biometrics (ICB 2016), Honorable Mention Paper Award.

Copyright © 2019. All rights reserved by Faculty of Electrical and Computer Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, Bangladesh. Developed by Mamun, CUET