An image recognition method based on multiple BP neural networks fusion

被引：0

作者：

Ni, JJ ^{[1
]}

Ma, XP ^{[1
]}

Xu, LZ ^{[1
]}

Wang, JY ^{[1
]}

机构：

[1] China Univ Min & Technol, Informat & Elect Engn Coll, Xuzhou, Jiangsu Provinc, Peoples R China

来源：

ICIA 2004: Proceedings of 2004 International Conference on Information Acquisition | 2004年

关键词：

image recognition; multiple BP neural networks; D-S theory of evidence;

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：

With respect to the limitation of the image recognition method by single BP neural network, a new method based on multiple BP neural networks with D-S theory is proposed. By using this method to synthesize each image recognition result of single BP neural network, we can improve the performance of the image recognition. The results of the computer simulation and experiment show that the new method is effective.

引用

页码：323 / 326

页数：4

共 6 条

[1] SHAFER-DEMPSTER REASONING WITH APPLICATIONS TO MULTISENSOR TARGET IDENTIFICATION SYSTEMS
BOGLER, PL
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1987, 17 (06): : 968 - 977
[2] Jia Caichao, 2001, Acta Optica Sinica, V21, P177
[3] KLENA VC, 1980, IEEE T AUTOMATIC CON, V25, P164
[4] NI J, 2000, J LIANYUNGANG COLL C, V13, P34
[5] YANG W, 2000, MICROCOMPUTER APPL, V16, P22
[6] [于洪珍 Yu Hongzhen], 2003, [中国矿业大学学报. 自然科学版, Journal of China University of Mining & Technology], V32, P148

← 1 →