Face recognition under variations in illumination using the phase of fractional Fourier transform

Abstract

In face recognition, one of the major challenges arises due to the illumination variations. Since the fractional Fourier transform (FRFT) is robust to illumination variations, a novel method is proposed for the face recognition using the phase of the FRFT. The problem of phase wrapping is dealt by the use of the sine and cosine functions for the phase spectrum instead of the phase directly. Experimental results on Yale-B database shows that the proposed method is effective than the existing methods.