Abstract

In the last years, face recognition has become a popular area of research in computer vision, it is typically used in network security systems and access control systems but it is also useful in other multimedia information processing areas. Performance of the face verification system depends on many conditions. One of the most problematic is varying illumination condition. In this paper, we discuss the preprocessing method to solve one of the common problems in face images, due to a real capture system i.e. lighting variations. The different stages include gamma correction, Difference of Gaussian (DOG) filtering and contrast equalization. Gamma correction enhances the local dynamic range of the image in dark or shadowed regions while compressing it in bright regions and is determined by the value of 3B3;. DOG filtering is a grey scale image enhancement algorithm that eliminates the shadowing effects. Contrast equalization rescales the image intensities to standardize a robust measure of overall intensity variations. The technique has been applied to Yale-B data sets, Face Recognition Grand Challenge (FRGC) version 2 Experiment 4 and a real time created data set.