Biometric face recognition using Mexican hat wavelet kernel based SVM

Face recognition for biometric purposes has an advantage of being a non-contact process. Various face recognition algorithms has been proposed in the literature. The face recognition system mainly consists of two steps i.e. feature extraction / reduction and classification. One of the most popular tool, Principal Component Analysis (PCA) is used for feature extraction. For classification purpose, various distance classifiers as well as Support Vector Machines (SVM) with various kernels are used. Radial basis function (RBF) kernel in SVM is one of the widely used kernels for this purpose. In this paper, Mexican hat wavelet kernel based SVM is proposed for classification and the comparison of this kernel with other classification methods are examined. The proposed kernel performs better in terms of no. of support vectors compared to RBF kernel and the recognition rate is also high with less number of features.