中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Spatial relationship representation for visual object searching

文献类型：期刊论文

作者Miao, Jun1; Duan, Lijuan2; Qing, Laiyun3; Gao, Wen5; Chen, Xilin; Yuan, Yuan4
刊名NEUROCOMPUTING
出版日期2008-06-01
卷号71期号:10-12页码:1813-1823
关键词sparse coding spatial relationship visual context neural network object searching
ISSN号0925-2312
DOI10.1016/j.neucom.2007.11.030
英文摘要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.
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000257413300005
出版者ELSEVIER SCIENCE BV
源URL[http://119.78.100.204/handle/2XEOYT63/11081]  
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。