Computer Vision: A Plea for a Constructivist View

  • Catherine Garbay
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5651)

Abstract

Computer vision is presented and discussed under two complementary views. The positivist view provides a formal background under which vision is approached as a problem-solving task. By contrast, the constructivist view considers vision as the opportunistic exploration of a realm of data. The former view is rather well supported by evidence in neurophysiology while the latter view rather relies on recent trends in the field of distributed and situated cognition. The notion of situated agent is presented as a way to design computer vision systems under a constructivist hypothesis. Various applications in the medical domain are presented to support the discussion.

Keywords

Computer Vision Distributed Cognition Situated Agents Medical Image Processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Paragios, N., Chen, Y., Faugeras, O.: Preface. In: Paragios, N., Chen, Y., Faugeras, O. (eds.) The Handbook of Mathematical Models in Computer Vision, pp. 1–5. Springer, Heidelberg (2005)Google Scholar
  2. 2.
    Desolneux, A., Moisan, L.N., Morel, J.M.: From Gestalt Theory to Image Analysis : A Probabilistic Approach. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Kokkinos, I., Deriche, R., Faugeras, O., Maragos, P.: A Computational Analysis and Learning for a Biologically Motivated Model of Boundary Detection. Neurocomputing 71, 1798–1812 (2008)CrossRefGoogle Scholar
  4. 4.
    Thorpe, S.J., Guyonneaua, R., Guilbauda, N., Allegrauda, J.-M., VanRullen, R.: SpikeNet: Real-Time Visual Processing with one Spike per Neuron. Neurocomputing 58–60, 857–864 (2004)Google Scholar
  5. 5.
    Hutchins, E.: Cognition in the Wild. MIT Press, Cambridge (1995)Google Scholar
  6. 6.
    Suchman, L.A.: Plans and Situated Action: the Problem of Human-Machine Interaction. In: Pea, R., Brown, J.S. (eds.). Cambridge University Press, Cambridge (1987)Google Scholar
  7. 7.
    Varela, F., Thomson, E., Rosch, E.: L’Inscription Corporelle de l’Esprit, Le Seuil, Paris (1993)Google Scholar
  8. 8.
    Nardi, B.A.: Studying Context: a Comparison of Activity Theory, Situated Action Models and Distributed Cognition. In: Nardi, B.A. (ed.) Context and Consciousness: Activity Theory and Human-Computer Interaction. MIT Press, Cambridge (1996)Google Scholar
  9. 9.
    Weyns, D., Steegmans, E., Holvoet, T.: A Model for Active Perception in Situated Multi-Agent Systems. Applied Artificial Intelligence 18, 867–883 (2004)CrossRefGoogle Scholar
  10. 10.
    Bianchi, N., Bottoni, P., Spinu, C., Garbay, C., Mussio, P.: Situated Image Understanding in a Multi-Agent Framework. International Journal of Pattern Recognition and Artificial Intelligence 12, 595–624 (1998)CrossRefGoogle Scholar
  11. 11.
    Resnick, L.B.: Shared Cognition: Thinking as Social Practice, Perspectives on Socially Shared Cognition. In: Resnick, L.B., Levine, J.M., Thistle, S.D. (eds.), pp. 1–20. American Psychological Association, Washington (1991)Google Scholar
  12. 12.
    Minsky, M.: The Society of Mind. Simon and Shuster, New York (1985)Google Scholar
  13. 13.
    Shariatpanahi, H.F., Batmanghelich, N., Kermani, A.R.M., Ahmadabadi, M.N., Soltanian-Zadeh, H.: Distributed Behavior-Based Multi-Agent System for Automatic Segmentation of Brain MR Images. In: International Joint Conference on Neural Networks, Vancouver, BC, Canada, pp. 4535–4542 (2006)Google Scholar
  14. 14.
    Bovenkamp, E.G.P., Dijkstra, J., Bosch, J.G., Reiber, J.H.C.: Multi-Agent Segmentation of IVUS Images. Pattern Recognition 4, 647–663 (2004)CrossRefGoogle Scholar
  15. 15.
    Maes, P.: Situated Agents can have Goals. In: Maes, P. (ed.) Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back, pp. 49–70. MIT Press, London (1990)Google Scholar
  16. 16.
    Germond, L., Dojat, M., Taylor, C.J., Garbay, C.: A Cooperative Framework for Segmentation of MRI Brain Scans. Artificial Intelligence in Medicine 20, 77–93 (2000)CrossRefPubMedGoogle Scholar
  17. 17.
    Spinu, C., Garbay, C., Chassery, J.M.: A Cooperative and Adaptive Approach to Medical Image Segmentation. In: Wyatt, J.C., Stefanelli, M., Barahona, P. (eds.) AIME 1995. LNCS, vol. 934, pp. 379–390. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  18. 18.
    Boucher, A., Doisy, A., Ronot, X., Garbay, C.: A society of Goal-Oriented Agents for the Analysis of Living Cells. Artificial Intelligence in Medecine 14, 183–199 (1998)CrossRefGoogle Scholar
  19. 19.
    Scherrer, B., Dojat, M., Forbes, F., Garbay, C.: Agentifiation of Markov Model Based Segmentation: Application to MRI Brain Scans. Artificial Intelligence in Medicine 46, 81–95 (2009)CrossRefPubMedGoogle Scholar
  20. 20.
    Oulasvirta, A., Tamminen, S., Höök, K.: Comparing Two Approaches to Context: Realism and Constructivism. In: Proc of the 4th Decennial Conference on Critical Computing: between Sense and Sensibility, Aarhus, Denmar, pp. 195–198 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Catherine Garbay
    • 1
  1. 1.Laboratoire d’Informatique de GrenobleCNRS-Université de Grenoble, Batiment IMAG BSaint Martin d’HèresFrance

Personalised recommendations