Artificial neural network-based face recognition

被引:0
作者
Réda, A [1 ]
Aoued, B [1 ]
机构
[1] Univ Djillali Liabes Sidi Bel Abbes, Dept Comp Sci, EEDIS, Evolutionary Engn & Distributed Informat Syst Lab, Sidi Bel Abbes, Algeria
来源
ISCCSP : 2004 FIRST INTERNATIONAL SYMPOSIUM ON CONTROL, COMMUNICATIONS AND SIGNAL PROCESSING | 2004年
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This document demonstrates how a face recognition system can be designed with artificial neural network. Note that the training process did not consist of a single call to a training function. Instead, the network was trained several times on various input ideal and noisy images, the images which contents faces. In this case training a network on different sets of noisy images forced the network to learn how to deal with noise, a common problem in the real world.
引用
收藏
页码:439 / 442
页数:4
相关论文
共 9 条
[1]  
ADJOUDJ R, 2002, THESIS U DJILLALI LI
[2]  
BEYMER DJ, 1996, THESIS MIT
[3]  
DAUGMAN J, 1997, IEEE PAMI, V19
[4]  
Demuth H., 1998, NEURAL NETWORK TOOLB
[5]  
HSU RL, 2002, THESIS MICHIGAN STAT
[6]  
MITCHELL T, 1997, NEURAL NET FACE IMAG
[7]  
NORRIS JS, 1999, THESIS MIT US
[8]  
ROWLEY HA, 1999, THESIS CARNEGIEMELLO
[9]  
TIAN YL, 1999, RECOGNIZING ACTION U