The Truth about Corel - Evaluation in Image Retrieval

  • Henning Müller
  • Stephane Marchand-Maillet
  • Thierry Pun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2383)


To demonstrate the performance of content-based image retrieval systems (CBIRSs), there is not yet any standard data set that is widely used. The only dataset used by a large number of research groups are the Corel Photo CDs. There are more than 800 of those CDs, each containing 100 pictures roughly similar in theme. Unfortunately, basically every evaluation is done on a different subset of the image sets thus making comparison impossible.

In this article, we compare different ways of evaluating the performance using a subset of the Corel images with the same CBIRS and the same set of evaluation measures. The aim is to show how easy it is to get differing results, even when using the same image collection, the same CBIRS and the same performance measures. This pinpoints the fact that we need a standard database of images with a query set and corresponding relevance judgments (RJs) to really compare systems.

The techniques used in this article to “enhance” the apparent performance of a CBIRS are commonly used, sometimes described, sometimes not. They all have a justification and seem to change the performance of a CBIRS but they do actually not. With a larger subset of images it is of course much easier to generate even bigger differences in performance. The goal of this article is not to be a guide of how to make the “apparent” performance of systems look good, but rather to make readers aware of CBIRS evaluations and the importance of standardized image databases, queries and RJ.


Image Retrieval Image Database Average Rank Relevance Feedback Relevant Image 
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.
    Proceedings of the ACM Multimedia Workshop on Multimedia Information Retrieval (ACM MIR 2001), Ottawa, Canada, October 2001. The Association for Computing Machinery.Google Scholar
  2. 2.
    C. Carson, S. Belongie, H. Greenspan, and J. Malik. Color-and texture-based segmentation using em and its application to image querying and classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002 (to appear).Google Scholar
  3. 3.
    K. Chakrabarti, K. Porkaew, and S. Mehrotra. Efficient query refinement in multimedia databases. In Proceedings of the 16th International Conference on Data Engineering (ICDE2000), San Diego, CA, USA, March 1–3 2000. IEEE Computer Society.Google Scholar
  4. 4.
    C. W. Cleverdon, L. Mills, and M. Keen. Factors determining the performance of indexing systems. Technical report, ASLIB Cranfield Research Project, Cranfield, 1966.Google Scholar
  5. 5.
    L. Duan, W. Gao, and J. Ma. A rich get richer strategy for content-based image retrieval. In R. Laurini, editor, Fourth International Conference On Visual Information Systems (VISUAL’ 2000), number 1929 in Lecture Notes in Computer Science, pages 290–299, Lyon, France, November 2000. Springer-Verlag.Google Scholar
  6. 6.
    K.-S. Goh, E. Chang, and K.-T. Cheng. Support vector machine pairwise classifiers with error reduction for image classification. In ACMMIR2001 [1], pages 32–37.Google Scholar
  7. 7.
    D. Harman. Overview of the first Text REtrieval Conference (TREC-1). In Proceedings of the first Text REtrieval Conference (TREC-1), pages 1–20, Washington DC, USA, 1992.Google Scholar
  8. 8.
    D. P. Huijsmans and N. Sebe. Extended performance graphs for cluster retrieval. In Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2001), pages 26–31, Kauai, Hawaii, USA, December 9–14 2001. IEEE Computer Society.Google Scholar
  9. 9.
    IEEE. Proceedings of the second International Conference on Multimedia and Exposition (ICME’2001), Tokyo, Japan, August 2001. IEEE.Google Scholar
  10. 10.
    F. Jing, B. Zhang, F. Lin, W.-Y. Ma, and H.-J. Zhang. A novel region-based image retrieval method using relevance feedback. In ACMMIR2001 [1], pages 28–31.Google Scholar
  11. 11.
    C. Jörgensen and P. Jörgensen. Testing a vocabulary for image indexing and ground truthing. In G. Beretta and R. Schettini, editors, Internet Imaging III, volume 4672 of SPIE Proceedings, pages 207–215, San Jose, California, USA, January 21–22 2002. (SPIE Photonics West Conference).Google Scholar
  12. 12.
    C. S. Lee, W.-Y. Ma, and H. Zhang. Information embedding based on user’s relevance feedback in image retrieval. In S. Panchanathan, S.-F. Chang, and C.-C. J. Kuo, editors, Multimedia Storage and Archiving Systems IV (VV02), volume 3846 of SPIE Proceedings, pages 294–304, Boston, Massachusetts, USA, September 20–22 1999. (SPIE Symposium on Voice, Video and Data Communications).Google Scholar
  13. 13.
    M. Li, Z. Chen, L. Wenyin, and H.-J. Zhang. A statistical correlation model for image retrieval. In ACMMIR2001 [1], pages 42–45.Google Scholar
  14. 14.
    W. Y. Ma, Y. Deng, and B. S. Manjunath. Tools for texture-and color-based search of images. In B. E. Rogowitz and T. N. Pappas, editors, Human Vision and Electronic Imaging II, volume 3016 of SPIE Proceedings, pages 496–507, San Jose, CA, February 1997.Google Scholar
  15. 15.
    H. Müller, W. Müller, S. Marchand-Maillet, D. M. Squire, and T. Pun. Automated benchmarking in content-based image retrieval. In ICME’2001 [9], pages 321–324.Google Scholar
  16. 16.
    H. Müller, W. Müller, D. M. Squire, S. Marchand-Maillet, and T. Pun. Performance evaluation in content-based image retrieval: Overview and proposals. Pattern Recognition Letters, 22(5):593–601, April 2001.Google Scholar
  17. 17.
    H. Müller, W. Müller, D. M. Squire, Z. Pecenović, S. Marchand-Maillet, and T. Pun. An open framework for distributed multimedia retrieval. In Recherche d’Informations Assistée par Ordinateur (RIAO’2000) Computer-Assisted Information Retrieval, volume 1, pages 701–712., Paris, France, apr 12–14 2000.Google Scholar
  18. 18.
    M. Ortega, Y. Rui, K. Chakrabarti, K. Porkaew, S. Mehrotra, and T. S. Huang. Supporting ranked boolean similarity queries in MARS. IEEE Transactions on Knowledge and Data Engineering, 10(6):905–925, December 1998.Google Scholar
  19. 19.
    F. Qian, M. Li, W.-Y. Ma, F. Ling, and B. Zhang. Alternating features spaces in relevance feedback. In ACMMIR2001 [1], pages 14–17.Google Scholar
  20. 20.
    G. Salton. The SMART Retrieval System, Experiments in Automatic Document Processing. Prentice Hall, Englewood Cliffs, New Jersey, USA, 1971.Google Scholar
  21. 21.
    J. R. Smith and S.-F. Chang. VisualSEEk: a fully automated content-based image query system. In The Fourth ACM International Multimedia Conference and Exhibition, Boston, MA, USA, November 1996.Google Scholar
  22. 22.
    K. Sparck Jones and C. van Rijsbergen. Report on the need for and provision of an ideal information retrieval test collection. British Library Research and Development Report 5266, Computer Laboratory, University of Cambridge, 1975.Google Scholar
  23. 23.
    D. M. Squire, W. Müller, H. Müller, and J. Raki. Content-based query of image databases, inspirations from text retrieval: inverted files, frequency-based weights and relevance feedback. In The 11th Scandinavian Conference on Image Analysis (SCIA’99), pages 143–149, Kangerlussuaq, Greenland, June 7–11 1999.Google Scholar
  24. 24.
    D. M. Squire and T. Pun. A comparison of human and machine assessments of image similarity for the organization of image databases. In M. Frydrych, J. Parkkinen, and A. Visa, editors, The 10th Scandinavian Conference on Image Analysis (SCIA’97), pages 51–58, Lappeenranta, Finland, June 1997. Pattern Recognition Society of Finland.Google Scholar
  25. 25.
    N. Vasconcelos and A. Lippman. Learning over multiple temporal scales in image databases. In D. Vernon, editor, 6th European Conference on Computer Vision (ECCV2000), number 1842 in Lecture Notes in Computer Science, pages 33–47, Dublin, Ireland, June 26–30 2000. Springer-Verlag.Google Scholar
  26. 26.
    N. Vasconcelos and A. Lippman. A propabilistic architecture for content-based image retrieval. In Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’2000), pages 216–221, Hilton Head Island, South Carolina, USA, June 13–15 2000. IEEE Computer Society.Google Scholar
  27. 27.
    J. Z. Wand, J. Li, and G. Wiederhold. SIMPLIcity: Semantics-sensitive integrated matching for picture libraries. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23 No 9:1–17, 2001.Google Scholar
  28. 28.
    L. Zhu, C. Tang, A. Rao, and A. Zhang. Using thesaurus to model keyblock-based image retrieval. In ICME’2001 [9], pages 237–240.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Henning Müller
    • 1
  • Stephane Marchand-Maillet
    • 1
  • Thierry Pun
    • 1
  1. 1.Computer Vision GroupUniversity of GenevaSwitzerland

Personalised recommendations