Advertisement

An Empirical Investigation of the Scalability of a Multiple Viewpoint CBIR System

  • James C. French
  • Xiangyu Jin
  • W. N. Martin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3115)

Abstract

Our work in content-based image retrieval (CBIR) relies on content-analysis of multiple representations of an image which we term multiple viewpoints or channels. The conceptual idea is to place each image in multiple feature spaces and then perform retrieval by querying each of these spaces and merging the several responses. We have shown that a simple realization of this strategy can be used to boost the retrieval effectiveness of conventional CBIR. In this work we evaluate our framework in a larger, more demanding test environment and find that while absolute retrieval effectiveness is reduced, substantial relative improvement can be consistently attained.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    French, J.C., Watson, J.V.S., Jin, X., Martin, W.N.: Using multiple image representations to improve the quality of content-based image retrieval. Technical Report CS-2003-10, Dept. of Computer Science, Univ. of Virginia (2003)Google Scholar
  2. 2.
    French, J.C., Chapin, A.C., Martin, W.N.: Multiple viewpoints: A strategy for searching multimedia content. In: Workshop on Multimedia Content in Digital Libraries (2003)Google Scholar
  3. 3.
    Belkin, N., Cool, C., Croft, W., Callan, J.: The effect of multiple query representations on information retrieval system performance. In: Proc. of ACM SIGIR 1993, pp. 339–346 (1993)Google Scholar
  4. 4.
    Belkin, N., Kantor, P., Cool, C., Quatrain, R.: Combining evidence for information retrieval. In: Proc. of TREC-2, pp. 35–44 (1994)Google Scholar
  5. 5.
    Fox, E., Shaw, J.: Combination of multiple searches. In: Proc. of TREC-2, pp. 243–252 (1994)Google Scholar
  6. 6.
    Bartell, B., Cottrell, G., Belew, R.: Automatic combination of multiple ranked retrieval systems. In: Proc. of ACM SIGIR 1994, pp. 173–181 (1994)Google Scholar
  7. 7.
    Jin, X., French, J.C.: Improving image retrieval effectiveness via multiple queries. In: First ACM Inter. Workshop on Multimedia Databases, pp. 86–93 (2003)Google Scholar
  8. 8.
    French, J.C., Watson, J.V.S., Jin, X., Martin, W.N.: Integrating multiple multichannel cbir systems. In: Proc. Inter. Workshop on Multimedia Information Systems (MIS 2003), pp. 85–95 (2003)Google Scholar
  9. 9.
    French, J.C., Watson, J.V.S., Jin, X., Martin, W.N.: An exogenous approach for adding multiple image representations to content-based image retrieval systems. In: Proc. Seventh Inter. Symp. on Signal Processing and its Applications (2003)Google Scholar
  10. 10.
    Wenyin, L., Dumais, S., Sun, Y., Zhang, H., Czerwinski, M., Field, B.: Semiautomatic image annotation. In: Proc. of Human-Computer Interaction-Interact, pp. 326–333 (2001)Google Scholar
  11. 11.
    Shaw, J., Fox, E.: Combination of multiple searches. In: Proc. of TREC-3, pp. 105–108 (1995)Google Scholar
  12. 12.
    Vogt, C.: When does it make sense to linearly combine relevance scores. In: Proc. of ACM SIGIR 1997 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • James C. French
    • 1
  • Xiangyu Jin
    • 1
  • W. N. Martin
    • 1
  1. 1.Department of Computer ScienceUniversity of VirginiaCharlottesvilleUSA

Personalised recommendations