A Study on Illumination Invariant Face Recognition Methods Based on Multiple Eigenspaces

This paper presents two multiple illumination eigenspaces-based methods, RDEB and BPNNB, for solving the variable illumination problem of face recognition. The experiment shows that the methods have a high recognition ratio. In particular, BPNNB has outperformed the assumptive method which knows the illumination directions of faces and completes recognition in the specific eigenspace using eigenface method[2] for each face subset with a specific illumination direction.

[1]  Jianxin Wu,et al.  Efficient face candidates selector for face detection , 2003, Pattern Recognit..

[2]  Horst Bischof,et al.  Multiple eigenspaces , 2002, Pattern Recognit..

[3]  Dianxiang Xu,et al.  Illumination invariant face recognition based on neural network ensemble , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.

[4]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[6]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[7]  Tsuhan Chen,et al.  Pose invariant face recognition , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[8]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[9]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression (PIE) database , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.