Journal article
Individual stable space: An approach to face recognition under uncontrolled conditions
X Geng, ZH Zhou, K Smith-Miles
IEEE Transactions on Neural Networks | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | Published : 2008
Abstract
There usually exist many kinds of variations in face images taken under uncontrolled conditions, such as changes of pose, illumination, expression, etc. Most previous works on face recognition (FR) focus on particular variations and usually assume the absence of others. Instead of such a "divide and conquer" strategy, this paper attempts to directly address face recognition under uncontrolled conditions. The key is the individual stable space (ISS), which only expresses personal characteristics. A neural network named ISNN is proposed to map a raw face image into the ISS. After that, three ISS-based algorithms are designed for FR under uncontrolled conditions. There are no restrictions for t..
View full abstractGrants
Awarded by National Natural Science Foundation of China
Funding Acknowledgements
Manuscript received December 12, 2006; revised August 17, 2007 and December 21, 2007; accepted January 10, 2008. First published May 16, 2008; last published August 6, 2008 (projected). Part of this work was done when X. Geng was at the LAMDA Group, Nanjing University, Nanjing, China. The work of Z.-H. Zhou was supported by the National Science Foundation of China under Grants 60325207, 60635030, and 60721002 and the National High Technology Research and Development Program of China under Grant 2007AA01Z169.