Face Recognition from Video

Lecturer: 
FiDiPro Professor Xilin Chen
Date: 
23.2.2015 10:00

 

Infotech Oulu Lecture Series

Lecturer: FiDiPro Professor Xilin Chen, Chinese Academy of Sciences, China

Date: Friday, February 27, 2015
Time: 10:00 - 11:00
Room: TS127

Abstract

Face recognition from video typically needs to work on low-quality frame(s) captured under unconstrained conditions, which is challenging due to noise, blur, lower resolution, complex illumination, and head pose. Even for those methods working well on high resolution still image, their performances decrease dramatically on video. On the other hand, the consequent frames from video provide complementary information, and we believe this will play an important role in video case.

In this talk, I will show some of our efforts on face recognition from video. To take the advantage of multiple frames from video, we model the video as a set of images, and represent the set as a manifold. This allows us to utilize multiple frames in recognition. To deal with the low quality frames in video, we propose to alignment manifolds through a reference model. In frame level, we couple the procedure of face alignment and recognition in a loop. Some metrics are explored. I will report the results on different types of video.

Bio

Xilin Chen received the B.S., M.S., and Ph.D. degrees in computer science from Harbin Institute of Technology, China, in 1988, 1991, and 1994, respectively. He has been a professor with the Institute of Computing Technology, Chinese Academy of Sciences (CAS) from 2004. He has been a FiDiPro Professor since 2012. He has published one book and over 200 papers in refereed journals and proceedings in the areas of computer vision, pattern recognition, image processing, and multimodal interfaces. He is a Fellow of the China Computer Federation (CCF).

Last updated: 23.2.2015