Face Recognition System under Varying Lighting Conditions

Making recognition more reliable under uncontrolled lighting conditions is one of the most important challenges for practical face recognition systems. Other recognition systems don’t nullify most of the lighting variations. We tackle this by combining the strengths of robust illumination normalization, local texture-based face representations, distance transform based matching and kernel based feature extraction and multiple feature fusion. We present a simple and efficient preprocessing chain that eliminates most of the effects of changing illumination while still preserving the essential appearance details that are needed for recognition. We introduce Local Ternary Pattern (LTP), a generalization of the Local Binary Pattern (LBP) local texture descriptor less sensitive to noise. We further increase robustness by introducing Phase Congruency. The resulting method provides a face verification rate of 88.1% at 0.1% false accept rate. Experiments show that our preprocessing method outperforms several existing preprocessors for a range of feature sets, data sets and lighting conditions. We simulate this project using MATLAB software.