Face recognition method combined with gamma transform and Gabor transform

In order to extract facial features effectively, a face recognition method is proposed in this article, which combined with gamma transform and gabor transform on the basis of the traditional gabor filter method. First of all, the face images are processed with gamma transform, which can eliminate the effects of light and other nonlinear factors; and then decompose the face images by improved gabor transform. After that, instead the original face of the 5 scale and 8 orientations features of face images. At last extract M larger PCA (principal component analysis) characteristic on every Gabor feature matrix, and get the final 5∗8∗M characteristics, which are combined to form the final face identification feature. When tested in ORL faces database, the recognition rate of this algorithm is 7.5% higher than traditional PCA method.