Use of Image Regions in Context-Adaptive Image Classification

  • Ville Viitaniemi
  • Jorma Laaksonen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4306)


In this paper we describe and discuss our existing PicSOM software framework from the point of view of context-adaptive analysis of image contents, especially its method for using automatic image segmentation. We describe and experimentally validate a modification to the segment-using procedure that both essentially reduces the computational cost and slightly improves classification accuracy. Finally, we apply the segment-using methodology in qualitatively investigating the roles of primary objects and their context in classifying the images of the Pascal VOC Challenge 2006 database.


Feature Space Image Segmentation Visual Feature Target Object Image Database 
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.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001), Software available at:
  2. 2.
    Chen, Y., Wang, J.Z.: Looking beyond region boundaries: Region-based image retrieval using fuzzy feature matching. In: Multimedia Content-Based Indexing and Retrieval Workshop, INRIA Rocquencourt, France, September 24-25 (2001)Google Scholar
  3. 3.
    Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, Chichester (2001)CrossRefGoogle Scholar
  4. 4.
    ISO/IEC. Information technology - Multimedia content description interface - Part 3: Visual, 15938-3, 2002(E) (2002)Google Scholar
  5. 5.
    Jing, F., Li, M., Zhang, L., Zhang, H., Zhang, B.: Learning in region-based image retrieval. In: Bakker, E.M., Lew, M., Huang, T.S., Sebe, N., Zhou, X.S. (eds.) CIVR 2003. LNCS, vol. 2728, pp. 198–207. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  6. 6.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer Series in Information Sciences, vol. 30. Springer, Berlin (2001)MATHGoogle Scholar
  7. 7.
    Koikkalainen, P.: Progress with the tree-structured self-organizing map. In: 11th European Conference on Artificial Intelligence. European Committee for Artificial Intelligence (ECCAI) (August 1994)Google Scholar
  8. 8.
    Laaksonen, J., Koskela, M., Oja, E.: PicSOM—Self-organizing image retrieval with MPEG-7 content descriptions. IEEE Transactions on Neural Networks 13(4), 841–853 (2002)CrossRefGoogle Scholar
  9. 9.
    Laaksonen, J., Viitaniemi, V.: Emergence of ontological relations from visual data with self-organizing maps. In: Proceedings of the 9th Scandinavian Conference on Artificial Intelligence Scandinavian, Espoo, Finland (October 2006) (to appear)Google Scholar
  10. 10.
    Millet, C., Bloch, I., Hède, P., Moëllic, P.-A.: Using relative spatial relationships to improve individual region recognition. In: Proceedings of 2nd European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies, London, UK, November 2005, pp. 119–126 (2005)Google Scholar
  11. 11.
    Sjöberg, M., Laaksonen, J., Viitaniemi, V.: Using Image Segments in PicSOM CBIR System. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 1106–1113. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  12. 12.
    Viitaniemi, V., Laaksonen, J.: Focusing Keywords to Automatically Extracted Image Segments Using Self-Organising Maps. Studies in Fuzziness and Soft Computing, vol. 210. Springer, Heidelberg (to appear, 2006)Google Scholar
  13. 13.
    Viitaniemi, V., Laaksonen, J.: Techniques for still image scene classification and object detection. In: Kollias, S., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4132, pp. 35–44. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Wang, J.Z., Liu, J., Wiederhold, G.: SIMPLIcity: Semantics-sensitive integrated matching for picture libraries. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(9), 947–963 (2001)CrossRefGoogle Scholar
  15. 15.
    Wu, T.-F., Lin, C.-J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. Journal of Machine Learning Research 5, 975–1005 (2005)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ville Viitaniemi
    • 1
  • Jorma Laaksonen
    • 1
  1. 1.Laboratory of Computer and Information ScienceHelsinki University of TechnologyFinland

Personalised recommendations