Spatial relationship representation for visual object searching

doi:10.1016/j.neucom.2007.11.030

	Spatial relationship representation for visual object searching
	Miao, Jun 1; Duan, Lijuan 2; Qing, Laiyun 3; Gao, Wen 5; Chen, Xilin ; Yuan, Yuan 4
	2008-06-01
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	71 期号:10-12 页码:1813-1823
摘要	Image representation has been a key issue in vision research for many years. In order to represent various local image patterns or objects effectively, it is important to study the spatial relationship among these objects, especially for the purpose of searching the specific object among them. Psychological experiments have supported the hypothesis that humans cognize the world using visual context or object spatial relationship. How to efficiently learn and memorize such knowledge is a key issue that should be studied. This paper proposes a new type of neural network for learning and memorizing object spatial relationship by means of sparse coding. A group of comparison experiments for visual object searching between several sparse features are carried out to examine the proposed approach. The efficiency of sparse coding of the spatial relationship is analyzed and discussed. Theoretical and experimental results indicate that the newly developed neural network can well learn and memorize object spatial relationship and simultaneously the visual context learning and memorizing have certainly become a grand challenge in simulating the human vision system. (C) 2008 Elsevier B.V. All rights reserved.
关键词	sparse coding spatial relationship visual context neural network object searching
DOI	10.1016/j.neucom.2007.11.030
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000257413300005
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/11082
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Miao, Jun
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Digital Media Res Ctr, Beijing 100080, Peoples R China 2.Beijing Univ Technol, Coll Comp Sci & Technol, Beijing 100022, Peoples R China 3.Chinese Acad Sci, Grad Univ, Sch Informat Sci & Engn, Beijing 100049, Peoples R China 4.Aston Univ, Sch Engn & Appl Sci, Birmingham B4 7ET, W Midlands, England 5.Peking Univ, Inst Digital Media, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Miao, Jun,Duan, Lijuan,Qing, Laiyun,et al. Spatial relationship representation for visual object searching[J]. NEUROCOMPUTING,2008,71(10-12):1813-1823.
APA	Miao, Jun,Duan, Lijuan,Qing, Laiyun,Gao, Wen,Chen, Xilin,&Yuan, Yuan.(2008).Spatial relationship representation for visual object searching.NEUROCOMPUTING,71(10-12),1813-1823.
MLA	Miao, Jun,et al."Spatial relationship representation for visual object searching".NEUROCOMPUTING 71.10-12(2008):1813-1823.