The application of DBF neural networks for object recognition

CORC > 半导体研究所 > 中国科学院半导体研究所 > 中国科学院半导体研究所（2009年前）

	The application of DBF neural networks for object recognition
	Cao WM ; Hao F ; Wang SJ
刊名	information sciences
	2004
卷号	160 期号:1-4 页码:153-160
关键词	pattern recognition
ISSN号	0020-0255
通讯作者	cao, wm, zhejiang univ technol, inst intelligent informat syst, informat coll, hangzhou 310032, peoples r china. 电子邮箱地址: csann@zjut.edu.cn
中文摘要	on the basis of dbf nets proposed by wang shoujue, the model and properties of dbf neural network were discussed in this paper. when applied in pattern recognition, the algorithm and implement on hardware were presented respectively. we did experiments on recognition of omnidirectionally oriented rigid objects on the same level, using direction basis function neural networks, which acts by the method of covering the high dimensional geometrical distribution of the sample set in the feature space. many animal and vehicle models (even with rather similar shapes) were recognized omnidirectionally thousands of times. for total 8800 tests, the correct recognition rate is 98.75%, the error rate and the rejection rate are 0.5% and 1.25% respectively. (c) 2003 elsevier inc. all rights reserved.
学科主题	人工智能
收录类别	SCI
语种	英语
公开日期	2010-03-09
内容类型	期刊论文
源URL	[http://ir.semi.ac.cn/handle/172111/8130]
专题	半导体研究所_中国科学院半导体研究所（2009年前）
推荐引用方式 GB/T 7714	Cao WM,Hao F,Wang SJ. The application of DBF neural networks for object recognition[J]. information sciences,2004,160(1-4):153-160.
APA	Cao WM,Hao F,&Wang SJ.(2004).The application of DBF neural networks for object recognition.information sciences,160(1-4),153-160.
MLA	Cao WM,et al."The application of DBF neural networks for object recognition".information sciences 160.1-4(2004):153-160.