Analysing the Structure of Semantic Concepts in Visual Databases

  • Mats Sjöberg
  • Jorma Laaksonen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6731)


In this paper we study how the Self-Organizing Map (SOM) can be used in analysing the structure of semantic concepts in visual data. We investigate two data sets with concept labels provided by humans, and unlabelled data for which we utilise automatically detected concept membership scores by using models trained on a labelled data set. By arranging the concept memberships of visual objects as components of a vector, they can be used as the feature space for training a SOM. A visual and qualitative analysis of the SOM distributions of different concepts is augmented with a quantitative analysis based on measuring the Earth Mover’s Distance between the vector distributions on the 2D SOM surface. In particular we study the PASCAL VOC 2007 and TRECVID 2010 databases, which are two large image and video data sets.


Self-Organizing Map Earth Mover’s Distance concept detection high-level features image and video databases visualisation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hauptmann, A.G., Christel, M.G., Yan, R.: Video retrieval based on semantic concepts. Proceedings of the IEEE 96(4), 602–622 (2008)CrossRefGoogle Scholar
  2. 2.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer Series in Information Sciences, vol. 30. Springer, Berlin (2001)CrossRefzbMATHGoogle Scholar
  3. 3.
    Koikkalainen, P.: Progress with the tree-structured self-organizing map. In: 11th European Conference on Artificial Intelligence, pp. 211–215 (1994)Google Scholar
  4. 4.
    Laaksonen, J., Koskela, M., Oja, E.: PicSOM—Self-organizing image retrieval with MPEG-7 content descriptions. IEEE Transactions on Neural Networks, Special Issue on Intelligent Multimedia Processing 13(4), 841–853 (2002)CrossRefzbMATHGoogle Scholar
  5. 5.
    Rubner, Y., Tomasi, C., Guibas, L.J.: The Earth Mover’s Distance as a metric for image retrieval. Tech. Rep. CS-TN-98-86, Stanford University (1998)Google Scholar
  6. 6.
    van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(9), 1582–1596 (2010)CrossRefGoogle Scholar
  7. 7.
    Sjöberg, M., Koskela, M., Chechev, M., Laaksonen, J.: PicSOM experiments in TRECVID 2010. In: Proceedings of the TRECVID 2010 Workshop, Gaithersburg, MD, USA (November 2010)Google Scholar
  8. 8.
    Smeaton, A.F., Over, P., Kraaij, W.: Evaluation campaigns and TRECVid. In: MIR 2006: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 321–330. ACM Press, New York (2006)Google Scholar
  9. 9.
    Smeaton, A.F., Over, P., Kraaij, W.: High-Level Feature Detection from Video in TRECVid: a 5-Year Retrospective of Achievements. In: Divakaran, A. (ed.) Multimedia Content Analysis, Theory and Applications, pp. 151–174. Springer, Berlin (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mats Sjöberg
    • 1
  • Jorma Laaksonen
    • 1
  1. 1.Adaptive Informatics Research CentreAalto University School of ScienceAaltoFinland

Personalised recommendations