Selection of Facial Features using Genetic Algorithm under Different Illumination Conditions and Occlusions
Omid Sharifi M. Ç. YILDIZ M. ESKANDARI
AbstractThis paper concentrates on a face biometric system to investigate the face biometric and problems related to face recognition under different illumination variations, pose and partial occlusion. A face recognition system is developed to recognize face images based on Principal Components Analysis (PCA). The implemented scheme applies histogram equalization and mean-and-variance normalization for image preprocessing step to reduce the effects of the illumination. In order to improve the recognition performance, we implement a feature selection method based on Genetic Algorithm (GA). The implemented method improves the recognition performance of system by selecting the optimized sub set of PCA features and removing the irrelevant data. Several datasets of ORL, FERET and BANCA databases are used in order to test the robustness of the developed face recognition system.