Séminaire de Prof Makihara, Osaka University. Date : 24 février 2017, 10h00. Lieu : salle séminaire, Institut MICA, Hanoi University of Science and Technology

Intervenant :
Professor Makihara, Osaka University, Japan


Date : jeudi 24 février, 10h00
Lieu : salle "seminar room", 9ème étage, bâtiment B1, Institut MICA, Hanoi University of Science and Technology
Langue : le séminaire sera présenté en anglais


Gait recognition is a method of biometric person authentication from his/her unconscious walking manner. Unlike the other biometrics such as DNA, fingerprint, vein, and iris, the gait can be recognized even at a distance from a camera without subjects' cooperation, and hence it is expected to be applied to many fields: criminal investigation, forensic science, and surveillance. However, the absence of the subjects' cooperation may sometimes induces large intra-subject variations. In this talk, I'd like to briefly introduce recent progress on robust gait recognition against clothing, walking speed, and viewpoint, respectively. In addition, I introduce our large-scale gait data collection framework in conjunction with long-term exhibition of video-based gait analysis at a science museum. Finally, an online multi-modal biometric verification system using gait, face, and the height, will be introduced.