| 一种基于奇异值特征的神经网络人脸识别新途径 |
| |
| 引用本文： | 甘俊英,张有为.一种基于奇异值特征的神经网络人脸识别新途径[J].电子学报,2004,32(1):170-173. |
| |
| 作者姓名： | 甘俊英 张有为 |
| |
| 作者单位： | 1. 五邑大学信息学院,广东江门 529020;2. 北京航空航天大学电子信息工程学院,北京 100083 |
| |
| 摘 要： | 本文在Z Hong等人使用的奇异值分解(SVD)基础上,将人脸图像矩阵的奇异值作为识别特征,解决了奇异值处理、神经网络训练策略和竞争选择问题;运用BP网络进行识别,提出了一种基于奇异值特征的神经网络人脸识别新方法.基于ORL人脸数据库的多次反复实验结果表明,在大样本情况下,识别方法具有实现简单、识别速度快、识别率高的特点,为人脸的实时识别提供了一种新途径.
|
| 关 键 词： | 人脸识别 奇异值特征 神经网络 模式识别 |
| 文章编号： | 0372-2112(2004)01-0170-04 |
| 收稿时间： | 2001-11-08 |
A New Approach for Face Recognition Based on Singular Value Features and Neural Networks |
| |
| GAN Jun-ying ,ZHANG You-wei.A New Approach for Face Recognition Based on Singular Value Features and Neural Networks[J].Acta Electronica Sinica,2004,32(1):170-173. |
| |
| Authors: | GAN Jun-ying ZHANG You-wei |
| |
| Affiliation: | 1. School of Information,Wuyi University,Jiangmen,Guangdong 529020,China;2. School of Electronics and Information Engineering,Beihang University,Beijing 100083,China |
| |
| Abstract: | In this paper,singular value processing,training strategies of neural networks and competition selection are solved on the basis of singular value decomposition(SVD) applied by Z Hong et al.A new approach for face recognition on singular value features and neural networks is presented,in which singular values of face image matrix are used as features,and Back-Propagation(BP) network as recognition.Repeated experimental results on ORL(Olivetti Research Laboratory) database demonstrate that under the conditions of large samples recognition method has the characteristics of simple realization,rapid recognition speed and high recognition rate,and also profits real-time realization. |
| |
| Keywords: | face recognition singular value features neural networks pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
