An Efficient Preprocessing Technique for Face Recognition under Difficult Lighting Conditions

Abstract

Performance of the face verification system depends on many conditions. One of the most problematic is varying illumination condition. Making recognition more reliable under uncontrolled lighting conditions is one of the most important challenges for practical face recognition systems. This paper presents a simple and efficient preprocessing method that eliminates most of the effects of changing illumination and shadows while still preserving the essential appearance details that are needed for recognition. This preprocessing method run before feature extraction that incorporates a series of stages designed to counter the effects of illumination variations, local shadowing, and highlights while preserving the essential elements of visual appearance. Our method tackles this by combining the strengths of gamma correction, Difference Of Gaussian (DOG) filtering, contrast equalization. 1) Gamma correction enhances the local dynamic range of the image in dark or shadowed regions while compressing it in bright regions and at highlights. 2) DOG filtering that eliminates the shadowing effects while still preserving the essential appearance details that are needed for face recognition. 3) Contrast equalization rescales the image intensities to standardize a robust measure of overall contrast or intensity variations. The preprocessing method provides good performance on three sets that are widely used for testing under difficult lighting conditions: Extended Yale-B, Face Recognition Grand Challenge Version 2 experiment (FRGC-204), FERET datasets. The results obtained from the experiments showed that the illumination preprocessing methods significantly improves the recognition rate and it is a very important step in face verification system.