Multi-module Image Classification System

  • Wonil Kim
  • Sangyoon Oh
  • Sanggil Kang
  • Dongkyun Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4027)


In this paper, we propose an image classification system employing multiple modules. The proposed system hierarchically categorizes given sports images into one of the predefined sports classes, eight in this experiment. The image first categorized into one of the two classes in the global module. The corresponding local module is selected accordingly, and then used in the local classification step. By employing multiple modules, the system can specialize each local module properly for the given class feature. The simulation results show that the proposed system successfully classifies images with the correct rate of over 70%.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Jacobs, R.A., Jordan, M.I., Barto, A.G.: Task decomposition through competition in a modular connectionist architecture: The what and where vision task. Cognitive Science 15, 219–250 (1991)CrossRefGoogle Scholar
  2. 2.
    Waibel, A., Sawai, H., Shikano, K.: Modulraity and scaling in large phonemic neural networks. IEEE Transaction on Acoustics, Speech and Signal Processing 37, 1888–1897 (1989)CrossRefGoogle Scholar
  3. 3.
    Reilly, D.L., Scofield, C., Elbaum, C., Copper, L.N.: Learning system architectures composed of multiple learning modules. In: IEEE Int’l. Conf. Neural Networks, pp. 495–503 (1989)Google Scholar
  4. 4.
    Jacobs, R.A., Jordan, M.I.: Hierarchical mixtures of experts and the EM algorithm. Neural Computation 6, 181–214 (1994)CrossRefGoogle Scholar
  5. 5.
    Smieja, F.J.: Multiple network systems Minos modules: Task division and module dis-crimination. In: Proc. Of the 8th AISB conference on Artificial Intelligence, Leeds (April 1991)Google Scholar
  6. 6.
    Pratt, L.Y., Kamm, C.A.: Improving phoneme classification neural network through problem decomposition. In: IEEE Int’l. Joint Conf. Neural Networks, pp. 821–826 (1991)Google Scholar
  7. 7.
    Osherson, D.N., Weinstein, S., Stoli, M.: Modular learning. Computational Neuro-science, 369–377 (1990)Google Scholar
  8. 8.
    Haykins, S.: Neural Networks: A comprehensive Foundation. IEEE Press, Macmillan (1994)Google Scholar
  9. 9.
    Gorkani, M., Picard, R.W.: Textual orientation for sorting photos at a glance. In: Proceedings of International Conference on Pattern recognition, Jerusalem, Israel, October 1994, pp. 459–464 (1994)Google Scholar
  10. 10.
    Vailaya, A., Jain, A., Zhang, H.J.: On image classification: city images vs. land-scapes. In: Proceedings of IEEE Workshop on Content – Based Access of Image and Video Libraries (December 1998)Google Scholar
  11. 11.
    Szummer, M., Picard, R.W.: Indoor-outdoor image classification. In: Proceedings of IEEE International Workshop on Content – Based Access of Image and Video Libraries, Bombay, India (December 1998)Google Scholar
  12. 12.
    Ohta, Y.-I., Kanade, T., Sakai, T.: Color information for region segmentation. Computer Graphics and Image Processing 13(3), 222–241 (1980)CrossRefGoogle Scholar
  13. 13.
    Manjunath, B.S., Ma, W.Y.: Texture features for browsing and retrieval of im-age data. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(8) (August 1996)Google Scholar
  14. 14.
    Pass, G., Zabih, R.: Histogram refinement for content-based image retrieval. In: Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision, Sara-sota, Florida, USA (December 1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wonil Kim
    • 1
  • Sangyoon Oh
    • 2
  • Sanggil Kang
    • 3
  • Dongkyun Kim
    • 1
  1. 1.College of Electronics and Information Engineering at Sejong UniversitySeoulKorea
  2. 2.Computer Science Department at Indiana UniversityBloomingtonU.S.A.
  3. 3.Department of Computer ScienceThe University of SuwonGyeonggi-doKorea

Personalised recommendations