Optimal Kernel Marginal Fisher Analysis for Face Recognition

Nonlinear dimensionality reduction and face classifier selection are two key issues of face recognition. In this paper, an efficient face recognition algorithm named OKMFA is proposed. The core idea of the algorithm is as follows. First, the high-dimensional face images are mapped into lower-dimensional discriminating feature space by using the feature vector selection-based optimal kernel marginal Fisher analysis(KMFA), then the multiplicative update rule-based optimal SVM classifier is applied to recognize different facial images herein. Extensive experimental results on two benchmark face databases demonstrate the effectiveness and efficiency of the proposed algorithm.