A Novel Approach for Face Recognition Using PCA and Artificial Neural Network

Face recognition is a biometric tool for verification and authentication a facial recognition based verification system can further be deemed a computer application for automatically verifying or identifying a person in a digital image. Analytic (local features based) and holistic (global features based) are the two common approaches employed for face recognition approaches with acceptable success rates. In this paper, we present a hybrid features based face recognition Technique .It combines the local and global approaches to produce a high success rate face recognition system. . Experiments are carried out on the SDUMLA-HMT face database. Principal component analysis is used to compute global features while the local feature are computed configuring the central moment and Eigen vectors and the standard deviation of the nose, eyes and mouth segments of the human face as the decision support entities of Artificial neural network. Keywords— face recognition; analytic approach; holistic approach; hybrid features; central moment; standard deviation; eigen vectors; artificial neural network