HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE

Department of Computer Science Seminar
2016 Series

Full Ranking as Local Descriptor for Visual Recognition: A Comparison of Distance Metrics on Permutation Group

Dr. Chi Ho Chan
Research Fellow
University of Surrey

Date: January 25, 2016 (Monday)
Time: 10:30 - 11:30 am
Venue: RRS905, Sir Run Run Shaw Building, Ho Sin Hang Campus

Abstract
In this talk, the full ranking of a set of pixels is used as a local descriptor. In contrast to existing methods which use only partial ranking information, the full ranking encodes the complete comparative information among the pixels, while retaining invariance to monotonic photometric transformations. The descriptor is used within the bag-of-visual-words paradigm for visual recognition. We demonstrate that the choice of distance metric for assigning the descriptors to visual words is crucial to the performance, and provide an extensive evaluation of eight distance metrics for the permutation group Sn on four widely used face verification and texture classification benchmarks. The results demonstrate that (1) full ranking of pixels encodes more information than partial ranking, consistently leading to better performance; (2) full ranking descriptor can be trivially made rotation invariant; (3) the proposed descriptor applies to both image intensities and filter responses, and is capable of producing state-of-the-art performance.

Biography
Chi Ho Chan received his Ph.D. degree from the University of Surrey, U.K. in 2008. He is currently a research fellow at Centre for Vision, Speech and Signal Processing, University of Surrey. From 2002 to 2004, he served as a researcher at ATR International (Japan). His research interests include Image Processing, Pattern Recognition, Biometrics, and Vision-Based Human-Computer Interaction. He has publications in major biometrics and computer vision conferences and journals, including CHI, ICB, IJCB, IFS, PAMI.

********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)

http://www.comp.hkbu.edu.hk/v1/?page=seminars&id=363
Photos  Slides