Research on Face Recognition Based on Back Propagation Neural Network
Lingyun Shen, Baihe Lang, Tailin Han, Yang Li · 2012
A new method, face recognition based on back propagation neural network, is presented in this paper. The proposed method extracts feature from face image with differential projection and geometrical features into eigenvector which is classified by back propagation neural network. Besides our method, the principal component analysis (PCA)-based method, the linear discriminated analysis (LDA)-based method and the Markov Random Fields (MRF)-based method were also tested for comparisons. The experimental results on ORL face database show that the proposed method achieves an average recognition accuracy of over 98% by using only 13 features. Moreover, the recognition accuracy is enhanced effectively, and the computational complexity and feature dimensions are reduced greatly.