中文

Journal of Applied Sciences ›› 2011, Vol. 29 ›› Issue (2): 153-158.doi: 10.3969/j.issn.0255-8297.2011.02.008

• Signal and Information Processing • Previous Articles     Next Articles

Image Retrieval Based on Homology Continuity in Multi-dimensional Space

LIU Pei-zhong1;3, WANG Shou-jue1;2   

  1. 1. Information Science and Technology College, Xiamen University, Xiamen 361005, Fujian Province, China
    2. Chinese Academy of Sciences Suzhou Institute of Nano-tech and Nano-bionics,
    Suzhou 215123, Jiangsu Province, China
    3. College of Engineering, Huaqiao University, Quanzhou 362021, Fujian Province, China
    Abstract:
  • Received:2010-11-04 Revised:2011-03-09 Online:2011-03-23 Published:2011-03-23
  • About author:柳培忠，博士生，研究方向：多维空间仿生信息学理论以及视觉媒体检索，E-mail: liupeizhong0921@163.com；王守觉，中国科学院院士，研究方向：仿生模式识别理论和动漫自动化，E-mail: wsjue@semi.ac.cn
  • Supported by:

    国家自然科学基金(No.60753001)；国家“863”高技术研究发展计划基金(No.2006AA01Z123)资助

PDF

1937

Abstract:

Continuity exists when an object identifiable by computer changes from one state to another.We propose a similarity metric by combining homology continuity and biomimetic distance based on multidimensional space biomimetic informatics (MDSBI) to achieve efficient image retrieval. Experiments on the COREL image database show that the proposed method can effectively improve the image retrieval efficiency.

Key words:  image retrieval, multi-dimensional space biomimetic informatics (MDSBI), similarity measurement, image distance

CLC Number: