A face recognition method robust to pose variation

Author

Ying, Wang ; Lifang, Wu ; Ling, Tu ; Xue, Wu

Author_Institution

Sch. of Electron. Inf. & control Eng., Beijing Univ. of Technol., Beijing

fYear

2008

Firstpage

1600

Lastpage

1603

Abstract

In this paper, a face recognition method robust to pose variation is proposed. First, Cascade-MR-ASM is utilized to locate feature points in face image, then the location results are mapped into the public parameter space and the shape parameters are obtained. Then the frontal ASM model is obtained by setting zero to parameters related to pose. Then frontal face image is obtained by texture mapping. Finally, face recognition based on eigenface is finished using the K-Nearest Neighbor classifier. The experimental results in CMU_PIE show that the algorithm is robustness to variation of pose.

Keywords

eigenvalues and eigenfunctions; face recognition; feature extraction; image classification; image texture; pose estimation; shape recognition; K-nearest neighbor classifier; cascade multiresolution active shape model; eigenface; face image recognition method; image texture mapping; pose variation; public parameter space; Active appearance model; Active shape model; Clustering algorithms; Control engineering; Face recognition; Lighting; Robust control; Robustness; Shape control; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2008. ICSP 2008. 9th International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2178-7

Electronic_ISBN

978-1-4244-2179-4

Type

conf

DOI

10.1109/ICOSP.2008.4697441

Filename

4697441