一种矢量倍增算法的神经网络人脸识别方法

广东工业大学学报 ›› 2006, Vol. 23 ›› Issue (3): 108-112.

一种矢量倍增算法的神经网络人脸识别方法

广东工业大学信息工程学院；广东工业大学信息工程学院广东广州510640；广东广州510640；

出版日期:2006-06-02 发布日期:2006-06-02

Neural Network Face Recognition Based on Length Extension Technique

(Faculty of Information Engineering,Guangdong University of Technology,Guangzhou 510640,China)

Online:2006-06-02 Published:2006-06-02

摘要/Abstract

摘要： 针对神经网络人脸识别中训练速度慢的问题,深入研究输入矢量长度的变化对神经网络收敛速度的影响,提出了一种矢量倍增算法对神经网络进行优化.这种方法是对网络输入矢量的长度倍增,从而提高神经网络收敛速度.通过人脸识别实验系统验证了矢量倍增算法的实用性.

关键词: 人脸识别； KL变换； BP神经网络；矢量倍增算法；

Abstract: After a great deal of investigations on the principle of BP model and the structure of the neural network,this paper manages to demonstrate how to increase the convergent speed of the BP neural network by optimizing the input of the network.Further more,a creative optimization technique—length extension technique,is presented here to improve the performance of neural network.After lots of experiments,this paper successfully increases the convergent speed of the BP neural network.

Key words: face recognition； K-L expansion； BP neural network； length extension technique (LET)；

张辰；潘保昌；郑胜林；卢毅涛；. 一种矢量倍增算法的神经网络人脸识别方法[J]. 广东工业大学学报, 2006, 23(3): 108-112.

ZHANG Chen,PAN Bao-chang,ZHENG Sheng-lin,LU Yi-tao. Neural Network Face Recognition Based on Length Extension Technique[J]. Journal of Guangdong University of Technology, 2006, 23(3): 108-112.

参考文献

[1] 甘俊英,张有为. 基于BP神经网络的人脸识别[J]. 系统工程与电子技术. 2003(01)

[1] (美)MartinT.Hagan等著.神经网络设计[M]. 机械工业出版社, 2002

[1] M. Kirby,L. Sirovich.Application of the Karhunen–Loeve procedure for the characterization of human faces. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1990

[2] Matthew Turk,A lex Pentland.E igenfaces for Recognition. Journal of Cognitive Neuroscience . 1991

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed