Image Normalization Robust using Histogram Equalization and Logarithm Transform Frequency DCT Coefficients for Illumination in Facial Images

A presented. The used for image normalization discrete cosine transform (DCT) method is applied on the images captured under varying new approach illumination under varying lighting conditions is lighting conditions. Illumination variation is one of intractable crucial problems in face recognition and many lighting normalization approaches have been proposed in the past decades. Most of the illumination corresponds to low frequency region. Face recognition algorithms have to deal variations as well as various facial features of a human face dealing with variations between gallery and probe images. In this paper, we propose a scaling of low frequency DCT coefficients is utilized for normalization method, which performs adaptive preprocessing for each testing image according to its lighting attribute. A proper way of scaling low frequency DCT coefficients is utilized by illumination normalization. The images captured under varying illumination have low contrast. For contrast stretching the adaptive histogram equalization is applied on face images. The comparative results are provided to evaluate the imaging hardware, the face and eye detection algorithms, and the face recognition algorithms and systems, with respect to various factors, including illumination, eyeglasses, time lapse, and so on. To analyze our illumination normalization method, we have used Yale Face Database. The results show better appearance of images and have been discussed with other approaches.