A face recognition method robust to pose variation
Ying Wang, Lifang Wu, Ling Tu, Xue Wu · 2008
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.