人脸识别常用方法及其发展现状  

The Common Method and Development Status for Face Recognition

作　　者：王伟[1] 马建光[1] 

机构地区：[1]北京理工大学机电工程学院,北京100081

出　　处：《兵工自动化》2002年第1期49-51,共3页Ordnance Industry Automation

摘　　要：人脸识别的研究历史分为人脸面部特征人工识别、人脸人机交互识别、人脸机器自动识别3个阶段。人脸识别系统包括人脸特征检测与分割、人脸特征规范化、人脸表征和人脸识别4部分。根据表征方式的不同,人脸识别方法有:基于层次聚类的几何特征矢量模式识别法、基于代数特征矢量的特征矢量识别法、基于神经网络的人脸特征提取和分类器设计法。并详述了代数特征矢量法中经典的特征脸法的识别过程。近年国外采用小波分析的变换特征识别法,利用模式识别的最佳分割超平面分类识别法等是当前研究热点。The face recognition consists of 3 steps: manual recognition, man-machine interactive recognition and automatic recognition. The system recognition of face includes the detection and segmentation of facial feature, the normalization of facial feature, face representation and face recognition. According to the different face representation mode, there are four recognition methods. They are the mode recognition method based on geometry feature vector, the feature vector recognition method based on algebra feature vector, the facial feature extraction method based on NN and design method of sorter. The recognition process of eigenface face method in algebra feature vector method was particularly described. In the same time, the recognition method of transforming feature based on wavelet elastic matching and the sorting recognition method for optimum segmentation of super plane based on mode recognition was introduced in this paper.

关 键 词：人脸识别 面部特征提取 人脸表征方法 本征脸法 人工智能 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]