Image
Image
Image
Image
Image
Image
Image
Image
Image
Image



Search
»

Seminar abstract

Recognizing Faces by Matching Forehead with Chin

Shiguang Shan
Professor
Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS)


Abstract: In previous works of face recognition, similarity between faces is measured by comparing corresponding face components. That is to say, matching eyes with eyes and mouths with mouths etc.. In this talk, I will introduce our recent work on recognizing faces by matching non-corresponding facial components. In another word we found that faces can be recognized by matching forehead with chin, for example. Specifically, the problem are formulated as how to measure the possibility whether two non-corresponding face components belong to the same face, which is measured via canonical correlation analysis in our work. Experimental results show that it is feasible to recognize face via non-corresponding region matching. The proposed method provides an alternative and more flexible way to recognize faces. During the talk, some face recognition related demos will also be demonstrated.

Bio: Prof. Shiguang Shan received the M.S. degree in computer science from the Harbin Institute of Technology, Harbin, China, in 1999, and the Ph.D. degree in computer science from the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, in 2004. He has been with ICT, CAS since 2002 and a Professor since 2010. His research interests cover image analysis, pattern recognition, and computer vision. He especially focuses on face recognition related research topics, and has published more than 100 papers on the related research topics. He received the China’s State Scientific and Technological Progress Awards in 2005 for his work on face recognition technologies. One of his co-authored CVPR’08 papers won the “Best Student Poster Award Runner-up”. He also won the Silver Medal of “Scopus Future Star of Science Award” in 2009. He is a member of the IEEE.
  Name Size

Image
PoweredBy © LAMDA, 2022