| Biometrics, because of using the proper living creature characteristic of human body, is the totally brand new technique different from traditional personal identification method. Because it has the better safety, dependable with the usefulness, more and more people thoughtful of. In all kinds of methods, it is also one of the most active and challenging tasks for computer vision and pattern recognition in recent 30 years. Face recognition has a wide range of potential applications in the areas of public security, identification of certificate, entrance control and video surveillance.This paper mainly studies the approaches to the features extraction and recognition in the face database. The main contents are as follows:(1) This paper uses the means of Principal Component Analysis (PCA) base on the K-L transformation. PCA is the face recognition method based on whole feature. The result of experiment proves to be fast in computing speed and stabilization. The recognition effect to the expression and gesture is excellence. But this method have the localization. The rate of recognition is decided by the quality of the choosing the eigenvectors.(2) This paper adopts two Classification design: least distance Classification and cosine distance Classification. And experiments is used to compared the recognition effect with the two distance Classification.(3) This paper proposed a face recognition method based on K-L transformation and genetic algorithm (GA). In the method of PCA based on K-L transformation the eigenvectors corresponding to the biggest eigenvalues are chose. While these eigenvectors are not the best classification eigenspaces. The best recognition effect can not to be achieved. In this paper, GA is introduced to solve this problem. Genetic algorithm is applied to get the optimal eigenvectors form K-L transformation. The ORL database as well as cosine distance classifier was used to verify the proposed method, the experiment results shows that the method is effective. |
PDF Full Text Request