Face Recognition Based on Image Transformation

Abstract

Face recognition is a very challenging topic in the field of pattern recognition, since illumination, gestures and expressions of face images are always different. In this paper, feature extraction is carried out on face images respectively through conventional methods of wavelet transform, Fourier transform, DCT, etc. Then these image transform methods are combined to process the face images. Nearest-neighbor classifiers using Euclidean distance and correlation coefficients used as similarity are adopted to recognize transformed face images. By this method, when more than five face images in a face database (ORL database) are selected as training samples, with the rest as testing samples, correct recognition rate can be 97% or higher. When five face images are from Yale face database, the correct recognition rate can be as high as 94.5%.