The Research and Improvement of the Face Recognition Method Based on the BP Neural Network

The recognition of human faces is an important subject in the area of the computer pattern recognition,which has a wide range of applications.And the key is face detection and feature extraction.In this paper,we use BP neural network for the feature extraction and recognition,the choosing principle of the number of hiding layer cells are proposed,the initial values setting principle are also discussed.And the BP algorithm is improved.It improves the precision,reduces the training time and the calculation.