Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application

SEMI OpenIR > 中国科学院半导体研究所（2009年前）

	Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application
	Wang SJ; Chen X; Wang SJ Chinese Acad Sci Artificial Neural Networks Lab Inst Semicond POB 912 Beijing 100083 Peoples R China.
	2003
会议名称	International Joint Conference on Neural Networks
会议录名称	PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4
页码	2258-2262
会议日期	JUL 20-24, 2003
会议地点	PORTLAND, OR
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
出版者	IEEE
ISSN	1098-7576
ISBN	0-7803-7898-9
部门归属	chinese acad sci, artificial neural networks lab, inst semicond, beijing 100083, peoples r china
摘要	A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR)(1). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.
关键词	Pattern Recognition Neural Networks Biomimetic High Dimensional Geometry
学科领域	人工智能
主办者	Int Neural Network Soc.; IEEE Neural Networks Soc.
收录类别	CPCI-S
语种	英语
文献类型	会议论文
条目标识符	http://ir.semi.ac.cn/handle/172111/13631
专题	中国科学院半导体研究所（2009年前）
通讯作者	Wang SJ Chinese Acad Sci Artificial Neural Networks Lab Inst Semicond POB 912 Beijing 100083 Peoples R China.
推荐引用方式 GB/T 7714	Wang SJ,Chen X,Wang SJ Chinese Acad Sci Artificial Neural Networks Lab Inst Semicond POB 912 Beijing 100083 Peoples R China.. Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2003:2258-2262.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2805.pdf（290KB）			限制开放	--	请求全文