基于BP神经网络人脸识别方法.pdfVIP

计算机研究与发展990304 计算机研究与发展 JOURNAL OF COMPUTER RESEARCH AND DEVELOPMENT 1999年 第3期 No.3 1999 基于BP神经网络的人脸识别方法 金　忠　胡钟山　杨静宇 摘　要　人脸自动识别是计算机模式识别领域的一个活跃课题，有着十分广泛的应用 前景.文中提出了基于BP神经网络的人脸识别方法，讨论了人脸图像矢量的特征压缩问 题、网络隐含层神经元数选取问题、网络输入矢量的标准化处理问题以及网络连接权 值的初值选取问题.对由18人、每人12幅图像组成的人脸图像数据库做识别实验，实验 结果表明文中所设计的神经网络分类器比常用的最近邻分类器有效地降低了识别错误 率. 关键词　神经网络，特征压缩，模式识别，人脸识别 中图法分类号　TP18； TP391 A FACE RECOGNITION METHOD BASED ON THE BP NEURAL NETWORK JIN Zhong, HU Zhong-Shan, and YANG Jing-Yu (Department of Computer Science,Nanjing University of Science and Technology,Nanjing 210014) Abstract　The automatic recognition of human faces is an active subject in the area of computer pattern recognition, which has a wide range of potential applications. A face recognition method is put forward based on the BP neural network. Also discussed are the problem of feature compression of a face image vector, the problem of determining the number of hidden layers neural nodes, the problem of normalization of the input vector, and the problem of initialization of connection weights. Experiments have been conducted for a human face image database of 18 persons with 12 images per person. The recognition results show that compared with the 1-NN classifier, the neural network classifier designed can decrease the error rate efficiently. Key words　neural network, feature compression, pattern recognition, face recognition file:///E|/qk/jsjyjyfz/jsjy99/jsjy9903/990304.htm（第 1／5 页）2010-3-23 1:14:37 计算机研究与发展990304 1　引　言 ［1］ 　　人脸识别是模式识别领域的一个前沿课题，有着十分广泛的应用前景 ，例如 身份证识别，信用卡识别，驾驶证识别