Title :
A nonlinear approach for face sketch synthesis and recognition
Author :
Liu, Qingshan ; Tang, Xiaoou ; Jin, Hongliang ; Lu, Hanqing ; Ma, Songde
Author_Institution :
Dept. of Inf. Eng., Hong Kong Chinese Univ., China
Abstract :
Most face recognition systems focus on photo-based face recognition. In this paper, we present a face recognition system based on face sketches. The proposed system contains two elements: pseudo-sketch synthesis and sketch recognition. The pseudo-sketch generation method is based on local linear preserving of geometry between photo and sketch images, which is inspired by the idea of locally linear embedding. The nonlinear discriminate analysis is used to recognize the probe sketch from the synthesized pseudo-sketches. Experimental results on over 600 photo-sketch pairs show that the performance of the proposed method is encouraging.
Keywords :
computational geometry; face recognition; statistical analysis; face recognition system; face sketch recognition; face sketch synthesis; nonlinear discriminate analysis; photo-based face recognition; pseudosketch generation; pseudosketch synthesis; Databases; Face recognition; Geometry; Kernel; Laboratories; Linear discriminant analysis; Nearest neighbor searches; Nonlinear distortion; Pattern recognition; Probes;
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
Print_ISBN :
0-7695-2372-2
DOI :
10.1109/CVPR.2005.39