ImageAspect Finder/Difference-Amplifier: Focusing on Peripheral Information for Image Search and Browsing

  • Shinsuke Nakajima
  • Koji Zettsu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3399)


Conventional image search/browse systems are not useful enough. Because there is a limit to representing characteristics of images though image data has a diversity of characteristics. We develop Difference-Amplifier and ImageAspect finder that are image search and browsing system focusing on peripheral information of query/answer images. The Difference-Amplifier for relevance feedback can extract user’s requirements for image retrieval by amplifying difference between a user-selected image and unselected peripheral images. The ImageAspect Finder for image browsing can extract context of the image and other images that are used in the same context by analyzing surrounding text of link anchor that refers to the query image.


Image Retrieval Query Image Relevance Feedback Image Search Image Retrieval System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Nakajima, S., Tanaka, K.: Relative Queries and the Relative Cluster-Mapping Method. In: Lee, Y., Li, J., Whang, K.-Y., Lee, D. (eds.) DASFAA 2004. LNCS, vol. 2973, pp. 843–856. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Zettsu, K., Kidawara, Y., Tanaka, K.: Discovering Aspect-based Correlation of Web Contents for Cross-media Information Retrieval. In: Proceedings of the 2004 IEEE International Conference on Multimedia and Expo (ICME 2004), Taipei, Taiwan (June 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Shinsuke Nakajima
    • 1
  • Koji Zettsu
    • 1
    • 2
  1. 1.National Institute of Information and Communications(NICT)KyotoJapan
  2. 2.Graduate School of InformaticsKyoto UniversityKyotoJapan

Personalised recommendations