The Research And Application Of Face Recognition Methods Based On SVM And Wavelet

As the development of the society, there are increasing demands in effective automatic identity checking, Biometrics is a kind of technology using individual physiological or behavioral characteristics to verify identity. It provides a highly reliable and high stability approach to the identity recognition. Automated face recognition is one of the most concerned branches of biometrics and it is also the one of the most active and challenging tasks for computer vision and pattern recognition at present. Others, they can be used as features for identity check, among all the characteristics of human, the characteristics of face are the most direct means which are friendly and convenient and can easily be accepted by the customers. It is widely applied to public security and security department, such as mug shots retrieval, real-time video surveillance, bank cryptography and so on. Face recognition is an extensive and challenging research problem. Recently, significant progresses have been made in the technology of the face recognition. In this thesis, we first introduced the background and the main methods of the face recognition and then proposed a method based on the wavelet transform and support vector machine and negative selection for face recognition. Aiming at the studying of support vector machine is a kind of studying with the answer, the clustering algorithm is inducted, the facial feature clustered is used to train the support vector machine. Sometimes to obtain criterion frontal face image is full of difficulties in practical application, therefore we try to combine neural network and support vector machine to deal with multi-pose face image recognition. In this method, we first preprocessed the face, then the wavelet transform was used to obtain the stable low frequency sub-band of the image in relatively low dimensions and achieve the purpose to reduce the vector quantity of the picture at the same time, then discrete cosine transform was used to extract the central features of the images, the characteristic vector drawn out keeps main classifiable information in originally picture space, the rate of higher discernment and fine resisting noise performance are obtained. Comparing with the traditional PCA algorithm, the method proposed here significantly decreases the operation complexity, experimental results verified that the proposed algorithm has higher recognition rate compared whit other algorithm.