| With the development of network and communications technologies, the demand on the safety for information is growing. In recent years, a variety of human-based biometric identification technology has disappeared. Face recognition is the most important part of biometric identification. It is direct, friendly, convenient and can be easily accepted by users, so face recognition is being a hotspot of biometrics and has a wide application prospect.The key technology of face recognition is how to extract discriminant feature from a face image. In recent years, many feature extraction methods have been proposed. Among them, the subspace methods have become the most popular approach owing to their appealing properties, such as low time-consuming, good performance on expression and separation. This article will study the face recognition algorithm based on subspace. After deeply investigating the traditional subspace face recognition algorithm, a modified maximum margin criterion is proposed. A face recognition system based on weighted maximum margin criterion algorithm is simulated in MATLAB GUI environment. The main contributions of this thesis are summarized as follows:(1) Considering the defaults of convenient face recognition algorithm based on subspace, weighted maximum margin criterion algorithm is proposed in this article. This algorithm can resolve the small size sample problem in linear discriminate analysis. By weighting the scatter within class matrix, making the extracted features more classified information.(2) The proposed methods and the traditional subspace algorithm are compared in experiments, and experimental results have indicated that it's more effective in face recognition.(3) In the MATLAB GUI environment, creating a face recognition access control system user interface for the system simulation experiments. In the simulation system verified the feasibility of the proposed algorithm, and improved the system for lighting requirement. |
PDF Full Text Request