Face Recognition: An Optimized Localization Approach and Selected PZMI Feature Vector Using SVM Classifier

In this paper a system is developed for face recognition processes. After preprocessing of face images, for omitting the redundant information such as background and hair, the oval shape of face is approximated by an ellipse using shape information. Then the parameters (orientation and center coordinates) of this ellipse are optimized using Genetic Algorithm (GA). High order Pseudo Zernike Moment Invariant (PZMI) which has useful properties is utilized to produce feature vectors. We use GAs in combination with nearest neighbor classifier to select the optimal feature set for classification. Also, Support Vector Machines (SVMs) which has very good generalization ability has been used as a classifier with ERBF kernel function. Proposed approach has been applied on ORL and Yale databases and has shown a high classification rate with small number of feature elements.