Face Recognition Based On Digit Image Processing

With the developing of the technology of micro-electron, computer and Internet, the traditional identification methods meet challenge, such as using passwords and IC card. The research of new method for identification is necessary. Because of the unity of human body feature, people think of identification by use of biological features. By now, the fingerprint identification and the iris identification have high recognize rate. Compared to other biological features, the face has direct, friendly and convenient character. In recently, many international researchers focus on the automatic face recognition and have done much study on it.Automatic face recognition from images is difficult, especially the problem based on small specimen. This thesis surveys the current status of automatic face recognition system, outlines its structure and modules. The techniques of pre-processing, feature extraction and recognition are studied in the thesis work. A face recognition system based on VC is developed.In the stage of image pre-processing, lighting compensation and hist equality are done first because that PCA method is sensitive to illumination. Considering the characters of data-density and compute-density, this thesis introduces wavelet transform. By wavelet transform, the information of high frequency is filtered, the information of low frequency is remained. So the dimension of image vectors is greatly decreased after wavelet transform.Principal Component Analysis (PCA) method is used to extract feature in this thesis. The design of classifier is crucial to face recognition. A combination between minimum distance classifier and BP neural network classifier is presented in thesis.Experimental results show that the algorithm presented by this thesis is not sensitive to pose and expression, the new classifier is superior to the single classifier.Feature researches are pointed out considering the experiences of our system and the development trend.