Image Interpretation by Combining Ontologies and Bayesian Networks

  • Spiros Nikolopoulos
  • Georgios Th. Papadopoulos
  • Ioannis Kompatsiaris
  • Ioannis Patras
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7297)

Abstract

A drawback of current computer vision techniques is that, in contrast to human perception that makes use of logic-based rules, they fail to benefit from knowledge that is provided explicitly. In this work we propose a framework that performs knowledge-assisted analysis of visual content using ontologies to model domain knowledge and conditional probabilities to model the application context. A bayesian network (BN) is used for integrating statistical and explicit knowledge and perform hypothesis testing using evidence-driven probabilistic inference. Our results show significant improvements compared to a baseline approach that does not make any use of context or domain knowledge.

Keywords

Bayesian Network Domain Knowledge Category Concept Application Context Probabilistic Inference 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Progress in Brain Research (2006)Google Scholar
  2. 2.
    Gokalp, D., Aksoy, S.: Scene classification using bag-of-regions representations. In: CVPR 2007, pp. 1–8 (June 2007)Google Scholar
  3. 3.
    Naphade, M.R., Huang, T.S.: A probabilistic framework for semantic video indexing, filtering, and retrieval. IEEE TMM 3(1), 141–151 (2001)Google Scholar
  4. 4.
    Luo, J., Savakis, A.E., Singhal, A.: A bayesian network-based framework for semantic image understanding. Pattern Recognition 38(6) (2005)Google Scholar
  5. 5.
    Kane, M.J., Savakis, A.E.: Bayesian network structure learning and inference in indoor vs. outdoor image classification. In: ICPR 2004, pp. 479–482 (2004)Google Scholar
  6. 6.
    Ding, Z., Peng, Y., Pan, R.: A bayesian approach to uncertainty modeling in owl ontology. In: Int. Conf. on Adv. in Intel. Sys. - Theory and Applications (2004)Google Scholar
  7. 7.
    Papadopoulos, G.T., Mezaris, V., Kompatsiaris, I., Strintzis, M.G.: Combining global and local information for knowledge-assisted image analysis and classification. EURASIP J. Adv. Sig. Proc. 2007(2), 18 (2007)Google Scholar
  8. 8.
    Horrocks, I.: Description Logics in Ontology Applications. In: Beckert, B. (ed.) TABLEAUX 2005. LNCS (LNAI), vol. 3702, pp. 2–13. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Manjunath, B.S., Ohm, J.R., Vinod, V.V., Yamada, A.: Colour and texture descriptors. IEEE TCSVT, Special Issue on MPEG-7 11, 703–715 (2001)Google Scholar
  10. 10.
    Adamek, N.M.T., O’Connor, N.: Region-based segmentation of images using syntactic visual features. In: WIAMIS 2005, Montreux, Switzerland (2005)Google Scholar
  11. 11.
    Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Verbeek, J., Triggs, B.: Region classification with markov field aspect models. In: CVPR 2007, pp. 1–8 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Spiros Nikolopoulos
    • 1
    • 2
  • Georgios Th. Papadopoulos
    • 1
  • Ioannis Kompatsiaris
    • 1
  • Ioannis Patras
    • 2
  1. 1.CERTH-ITI, Informatics and Telematics InstituteGreece
  2. 2.School of Electronic Engineering and Computer ScienceQMULUK

Personalised recommendations