Study of human face recognition based on principal component analysis (PCA) and direction basis function neural networks

The automatic recognition of human faces is a hot spot in the field of pattern recognition, which has a wide range of potential applications. In this paper, a novel approach to human face image recognition based on principal component analysis and direction basis function neural networks has been proposed. Preprocessing using direction basis function neural networks, human face images are successfully classified and recognized according to the output of DBFNN whose input is the eigenvector extracted from the human face images via nonlinear principal component analysis of a single layer neural network Recognition algorithms of Priority Ordered Architecture of DBF Neural Networks. Simulation results demonstrate the effectiveness and stability of the approach.