A multi-view face recognition based on combined feature with clonal selection

The profile view of a face provides a complementary information, it is very important to face recognition. This paper construct novel the classification system combining both frontal and profile views of faces can improve the classification accuracy and decrease cost time. In this paper. we apply Self-organizing Map (SOM) and Minor Component (MC) to extract face feature from multi-view, and combine these features vector to a new combined feature set. Immune Clonal. Selection Algorithm is applied to search for better feature sets trough rotation transformations, thus, one is help to reduce classifier cost. Then, Support Vector Machine (SVM) is used as classifier which have demonstrated high generalization capabilities. Simulation experiments were made on two different face test databases., achieving very high recognition result than PCA and Fisher methods with relative low classification cost.