Skip to Main Content
A novel approach for illumination normalization is proposed by exploiting the correlation of discrete cosine transform (DCT) low-frequency coefficients to illumination variations. The input image contrast is stretched using full image histogram equalization. Then the low-frequency DCT coefficients (except first) are re-scaled to lower value to compensate the illumination variations. The first (DC) coefficient is scaled to higher value for further contrast enhancement. The experiments are performed on the Yale B database and the results show that the performance of the proposed approach is better for the images with large illumination variations. The proposed technique is computationally efficient and can easily be implemented for real time face recognition system.
Date of Conference: 18-21 Dec. 2007