Gabor features-based classification using SVM for face recognition

In this paper we present a novel Gabor-SVM method for face recognition by integrating the Gabor wavelet representation of face images and SVM classifier. Gabor wavelets first derive desirable facial features characterized by spatial frequency, spatial locality and orientation selectivity to deal with the variations due to illumination and facial expression changes. The principal components analysis (PCA) method is then used to reduce the dimensionality of the extracted Gabor features. With the reduced Gabor features, SVM is trained and then employed to do the recognition tasks. The performance of Gabor-SVM method is compared with the standard PCA-NC (Eigenfaces) method and PCA-SVM method on a subset of AR face database. The experiment results demonstrate the efficiency and superiority of the proposed Gabor-SVM method.