An approach to face recognition based on wavelet decomposition, SPCA and SVM

On the basis of introducing and discussing the wavelet decomposition, principal component analysis and support vector machine, an approach to face recognition is proposed in this paper. Firstly, wavelet decomposition is used to reduce facial image dimension. Secondly, under the premise of not increasing the number of images, symmetric principal component analysis is employed to expand the sample size. Finally, the support vector machine is used for face classification and recognition. Experimental results show that, compared to traditional face recognition algorithms, the proposed approach can not only increase the recognition rate, but also can improve the efficiency of algorithms.