Experimental Face Identification System Based on Support Vector Machines

Abstract

The development of automatic visual control system is a very important research topic in computer vision. There is an complex task of development face identification system robust to the various quality of the images as light, face expression, glasses, beards, moustaches etc. We explore the wavelet transformation algorithms for reduction the source data space. We have realized an expansion of pixels values to the whole intensity range and the equalization of histogram for the elimination of the intensity difference. The support vector machines (SVM) technology has been use for the face recognition in our work.