Interaction of Control and Knowledge in a Structural Recognition System

  • Eckart Michaelsen
  • Michael Arens
  • Leo Doktorski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5803)

Abstract

In this contribution knowledge-based image understanding is treated. The knowledge is coded declaratively in a production system. Applying this knowledge to a large set of primitives may lead to high computational efforts. A particular accumulating parsing scheme trades soundness for feasibility. Per default this utilizes a bottom-up control based on the quality assessment of the object instances. The point of this work is in the description of top-down control rationales to accelerate the search dramatically. Top-down strategies are distinguished in two types: (i) Global control and (ii) localized focus of attention and inhibition methods. These are discussed and empirically compared using a particular landmark recognition system and representative aerial image data from GOOGLE-earth.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arens, M., Nagel, H.–H.: Quantitative Movement Prediction based on Qualitative Knowledge about Behavior. In: KI – Künstliche Intelligenz 2/2005, pp. 5–11 (2005)Google Scholar
  2. 2.
    Desolneux, A., Moisan, L., Morel, J.–M.: From Gestalt Theory to Image Analysis. Springer, Berlin (2008)CrossRefMATHGoogle Scholar
  3. 3.
    Dickmanns, E.: Expectation-based Dynamic Scene Understanding. In: Blake, A., Yuille, A. (eds.) Active Vision, pp. 303–335. MIT Press, MA (1993)Google Scholar
  4. 4.
    Hotz, L., Neumann, B., Terzic, K.: High-Level Expectations for Low-Level Image Processing. In: Dengel, A.R., Berns, K., Breuel, T.M., Bomarius, F., Roth-Berghofer, T.R. (eds.) KI 2008. LNCS (LNAI), vol. 5243, pp. 87–94. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Kanade, T.: Model Representations and Control Structures in Image Understanding. In: Reddy, R. (ed.) Proc. 5th Int. Joint Conf. on Artificial Intelligence (IJCAI 1977), Cambridge, MA, USA, August 1977, pp. 1074–1082. William Kaufman, San Francisco (1977)Google Scholar
  6. 6.
    Lütjen, K.: BPI: Ein Blackboard-basiertes Produktionssystem für die automatische Bildauswertung. In: Hartmann, G. (ed.) Mustererkennung 1986, 8. DAGM–Symposium, Paderborn, September 30 – October 2. Informatik Fachberichte 125, pp. 164–168. Springer, Heidelberg (1986)CrossRefGoogle Scholar
  7. 7.
    Marroitt, K., Meyer, B. (eds.): Visual Language Theory. Springer, Berlin (1998)Google Scholar
  8. 8.
    Matsuyama, T., Hwang, V.S.–S.: SIGMA a Knowledge-Based Aerial Image Understanding System. Plenum Press, New York (1990)Google Scholar
  9. 9.
    Michaelsen, E., Jäger, K.: A GOOGLE-Earth Based Test Bed for Structural Image-based UAV Navigation. In: FUSION 2009, Proc. on CD, Seattle, WA, USA, pp. 340–346 (2009) ISBN 978-0-9824438-0-4Google Scholar
  10. 10.
    Michaelsen, E., Doktorski, L., Arens, M.: Shortcuts in Production Systems – A way to include clustering in structural Pattern Recognition. In: Proc. of PRIA-9-2008, Nischnij Nowgorod, vol. 2, pp. 30–38 (2008) ISBN 978-5-902390-14-5Google Scholar
  11. 11.
    Michaelsen, E., Doktorski, L., Arens, M.: Making Structural Pattern Recognition Tractable by Local Inhibition. In: VISAPP 2009, Proc. on CD, Lisboa, Portugal, vol. 1, pp. 381–384 (2009) ISBN 978-989-8111-69-2Google Scholar
  12. 12.
    Niemann, H.: Pattern Analysis and Understanding. Springer, Berlin (1989)MATHGoogle Scholar
  13. 13.
    Tenenbaum, J.M., Barrow, H.G.: Experiments in Interpretation Guided Segmentation. Artificial Intelligence Journal 8(3), 241–274 (1977)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Eckart Michaelsen
    • 1
  • Michael Arens
    • 1
  • Leo Doktorski
    • 1
  1. 1.Research Institute for Optronics and Pattern Recognition FGAN-FOMEttlingenGermany

Personalised recommendations