Face Recognition Using Neural Network with Pca–mbp Algorithm

In this paper, a face recognition system for personal identification and verification using Principal Component Analysis (PCA) with Modified Back Propagation Neural Networks (MBPNN) is proposed. The dimensionality of face image is reduced by the PCA and the recognition is done by the MBPNN. The system consists of a database of a set of facial patterns for each individual. The characteristic features of PCA called “Eigen faces‟ are extracted from the stored images, which is combining with Modified Back-Propagation Neural Network for subsequent recognition of new images. Eigen faces are produced by transforming the pixels in an image to (x; y) coordinates and forming a matrix with the coordinates. The Eigen faces or the principal components of the faces are the eigenvectors of the matrix and it is the eigenvectors. These Eigen vectors are given as input to the neural networks which performs the recognition process. In this we studied the concepts, for better accuracy and minimization of errors; we introduced a Modified Back-Propagation (MBP) algorithm for Neural Network which leads an efficient and convenient result in Neural network for face recognition mechanism. Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult. Face recognition from the images is challenging due to the wide variability of face appearances and the complexity of the image background. Neural based Face recognition is robust and has better performance. Keywords---Eigen Values, Eigen Vector, Face Recognition, Modified Back-Propagation Neural Network, Modified Back-Propagation Algorithm, and Principal Component Analysis.