Face Recognition Based on Face Gabor Image and SVM

The paper proposes an effective algorithm for face recognition using face Gabor image and support vector machine (SVM). The face Gabor image is firstly derived by downsampling and concatenating the Gabor wavelets representations which are the convolution of the face image with a family of Gabor kernels, and then the 2D principle component analysis (2DPCA) method is applied to the face Gabor image to extract the feature space. Finally, support vector machine (SVM) is used to classify. Experimental results on ORL database show that the face Gabor image carries more discriminant information and the proposed method can achieve 99.5% recognition rate on full face dataset and achieve 98.0% recognition rate on unitary dataset.