基于支持向量机的自动人脸识别

首先应用K-L变换对人脸图像进行特征提取，然后利用支持向量机进行识别。由于支持向量机参数对其性能有较大影响，为此采用遗传算法对其参数进行选取。为了能用较少的特征个数得到较高的识别率以提高识别速度，对所需提取的有效特征个数一并进行了选择。算法既解决了支持向量机参数选取的难题，又能够利用较少的人脸特征得到较高的识别率。利用ORL人脸库进行仿真实验。得到了97．5％的正确识别结果，验证了算法的有效性。

Automatic Face Recognition Based on Support Vector Machine

This paper proposes an automatic face recognition method based on support vector machine(SVM), applies the method of K-L transformation to extract the features of face images and then put these features into SVM for recognition. As the parameters of SVM play a important role in the process of recognition, genetic algorithm(GA) is applied to search for the best parameters of SVM. At the same time, GA is also applied to select the number of features that should be extracted in the recognition in order to achieve a higher recognition rate with fewer features. In this way, the algorithm not only solves the problem of SVM's parameters selection but also gets a higher recognition rate with fewer features. Finally the ORL face image database is made use of to simulate and a recognition rate of 97.5% is achieved. The experimental result show the validity of the algorithm.