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
Salient region detection and segmentation for general object recognition and image understanding

文献类型：期刊论文

作者Huang TieJun2; Tian YongHong2; Li Jia1; Yu HaoNan2
刊名SCIENCE CHINA-INFORMATION SCIENCES
出版日期2011-12-01
卷号54期号:12页码:2461-2470
关键词object recognition image understanding visual saliency salient object segmentation visual dictionary
ISSN号1674-733X
DOI10.1007/s11432-011-4487-1
英文摘要General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open problem. In this paper, we propose a selective attention-driven model for general image understanding, named GORIUM (general object recognition and image understanding model). The key idea of our model is to discover recurring visual objects by selective attention modeling and pairwise local invariant features matching on a large image set in an unsupervised manner. Towards this end, it can be formulated as a four-layer bottomup model, i.e., salient region detection, object segmentation, automatic object discovering and visual dictionary construction. By exploiting multi-task learning methods to model visual saliency simultaneously with the bottom-up and top-down factors, the lowest layer can effectively detect salient objects in an image. The second layer exploits a simple yet effective learning approach to generate two complementary maps from several raw saliency maps, which then can be utilized to segment the salient objects precisely from a complex scene. For the third layer, we have also implemented an unsupervised approach to automatically discover general objects from large image set by pairwise matching with local invariant features. Afterwards, visual dictionary construction can be implemented by using many state-of-the-art algorithms and tools available nowadays.
资助项目National Natural Science Foundation of China[90820003] ; National Natural Science Foundation of China[60973055] ; National Basic Research Program of China[2009CB320906] ; Ministry of Education of China
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000297709400002
出版者SCIENCE PRESS
源URL[http://119.78.100.204/handle/2XEOYT63/12775]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Tian YongHong
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Peking Univ, Sch Elect Engn & Comp Sci, Natl Engn Lab Video Technol, Beijing 100871, Peoples R China
推荐引用方式
GB/T 7714		 Huang TieJun,Tian YongHong,Li Jia,et al. Salient region detection and segmentation for general object recognition and image understanding[J]. SCIENCE CHINA-INFORMATION SCIENCES,2011,54(12):2461-2470.
APA Huang TieJun,Tian YongHong,Li Jia,&Yu HaoNan.(2011).Salient region detection and segmentation for general object recognition and image understanding.SCIENCE CHINA-INFORMATION SCIENCES,54(12),2461-2470.
MLA Huang TieJun,et al."Salient region detection and segmentation for general object recognition and image understanding".SCIENCE CHINA-INFORMATION SCIENCES 54.12(2011):2461-2470.

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。