A novel method for face recognition under partial occlusion or facial expression variations

Thir paper presents a new techniqzre for face recognition that can cope with partial occlussion or shong vuriations in facial expression. The method hies to solve the face recognition problem Pom a near- holistic perspective. The main idea is to "eliminate" some features which may came a reduction of the recognition accuracy tinder occlwion or expression changing. To test and evaluate the performance of the new technique. a series of experiments have been carried out which have shown improved pei$onnance and robustness when compared to the classical PCA.

[1]  Jun Zhang,et al.  Pace recognition: eigenface, elastic matching, and neural nets , 1997, Proc. IEEE.

[2]  Peter Eisert,et al.  Eye Center Localization Using Adaptive Templates , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[3]  Aleix M. Martínez,et al.  Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[5]  Paulo Quintiliano,et al.  Face recognition based on eigenfeatures , 2001, International Symposium on Multispectral Image Processing and Pattern Recognition.