基于特征脸的人脸识别系统

提出了一种快速有效的人脸识别系统．针对特征脸方法只能识别标准正面人脸的局限性，设计了前端处理模块，首先计算待识别图像中人脸的倾斜角度，进行相应角度的旋转，然后剪切出人脸图像，进行尺寸调整，经过此处理后再进行特征脸识别．利用ORL人脸库和自建人脸库进行仿真实验，实验结果表明，本识别系统速度快，误识率低，具有实用性．

Face recognition system based on eigenface algorithm

A fast and effective face recognition system is proposed in this paper. In view of the limitation that can only recognize standard and obverse faces using eigenfaces, front-end processing module is designed. First, the inclined angle of a face image to be recognized is calculated, and the proper rotation is made, then the face image is cut and the size of the image is adjusted. After that processing, face recognition is executed with eigenfaces. The face recognition experiment with ORL face databases shows that the algorithm is fast and the recognition error of the system is low.