International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Face recognition is a progressive field of research which is facing many challenges. This paper proposes a method of Genetic Algorithm (GA) based neural network for feature selection that retains sufficient information for classification purposes. This method presents an integration of genetic algorithm with an artificial neural network classifier. The proposed system consists of four stages: eigen face approach or PCA is used for dimensionality reduction, LDA is used for feature extraction, Genetic Algorithm based feature selection and finally Back Propagation Neural Network (BPNN) is used for the classification of face images to a particular class. This method uses LDA and PCA for dimensionality reduction and feature extraction which overcomes the Small Sample Size (SSS) problem of LDA.