KERNEL SUPERVISED DISCRIMINANT PROJECTION AND ITS APPLICATION FOR FACE RECOGNITION

Abstract

Subspace analysis is an effective approach for face recognition. In this paper, a novel subspace method, called kernel supervised discriminant projection (KSDP), is proposed for face recognition. In the proposed method, not only discriminant information with intrinsic geometric relations is preserved in subspace, but also complex nonlinear variations of face images are represented by nonlinear kernel mapping. Extensive experiments are performed to test and evaluate the new algorithm. Experimental results on three popular benchmark databases, FERET, Yale and AR, demonstrate the effectiveness of the proposed method, KSDP.