Models and Descriptions in Machine Vision

  • Vito Roberto


The meaning of model and description is discussed in the framework of machine perception. An artificial intelligence perspective is adopted, viewing a model as a Knowledge Representation Language (KRL), and a description as a construct of a KRL. Generalised inference is a key feature, inextricably connected to all kinds of models. The latter are grouped into three basic schemes: relational, propositional and procedural, each of which motivated by the need to capture relevant aspects of perceptual tasks. The distinguishing features of the schemes are outlined. Profound links are emphasized between relational/structural and propositional/linguistic schemes, in analogy with mental representations in human beings. The need to further combine the schemes into unified, hybrid representation languages emerges as a trend in present and future research.


Knowledge Representation Machine Vision Semantic Network Relational Scheme Perceptual Task 
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.
    D. Ballard and CM. Brown, Computer Vision, Prentice Hall, Englewood Cliffs, NY (1982).Google Scholar
  2. 2.
    R.A. Brooks, Intelligence without Representation, Artificial Intelligence, Vol.47, pp. 139–159 (1991).CrossRefGoogle Scholar
  3. 3.
    R. Davis, H. Shrobe, and P. Szolovits, What Is a Knowledge Representation?, The AI Magazine, pp. 17-33 (1993).Google Scholar
  4. 4.
    D. Marr, Vision, Freeman, San Francisco, CA (1982).Google Scholar
  5. 5.
    M. Minsky, Logical Versus Analogical or Symbolic Versus Connectionist or Neat Versus Scruffy, The AI Magazine, pp. 34-51 (1991).Google Scholar
  6. 6.
    H. Niemann, G.F. Sagerer, S. Schröder, and F. Kümmert, ERNEST: A Semantic Network System for Pattern Understanding, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.12, No.9, pp. 883–905 (1990).CrossRefGoogle Scholar
  7. 7.
    R. Reiter and A.K. Mackworth, A Logical Framework for Depiction and Image Interpretation, Artificial Intelligence, Elsevier Science Publishers, Vol.41, pp. 125–155 (1989/90).CrossRefGoogle Scholar
  8. 8.
    J.J. Gibson, The Ecological Approach to Visual Perception, Houghton Mifflin, Boston, MA (1979).Google Scholar
  9. 9.
    J. Glasgow and D. Papadias, Computational Imagery, Cognitive Science, Vol.16, pp. 355–394 (1992).CrossRefGoogle Scholar
  10. 10.
    J. Mylopoulos and H. Levesque, An Overview on Knowledge Representation, in On Conceptual Modelling: Perspectives from Artificial Intelligence, Databases and Programming Languages, M. Brodie, J. Mylopoulos, and J.V. Schmidt eds., Springer Verlag, New York, NY, pp. 3–17 (1983).Google Scholar
  11. 11.
    R.A. Frost, Introduction to Knowledge Base Systems, Collins, London, UK (1986).Google Scholar
  12. 12.
    M.R. Genesereth and N.J. Nilsson, Logical Foundations of Artificial Intelligence, Morgan Kaufmann, Los Altos, CA (1987).Google Scholar
  13. 13.
    G.D. Hager, Task-Directed Sensor Fusion and Planning, Kluwer, Boston, MA (1990).CrossRefGoogle Scholar
  14. 14.
    R.C. Luo and M.G. Kay, Multisensor Integration and Fusion in Intelligent Systems, IEEE Transactions on Systems, Man and Cybernetics, Vol.SMC-19, No.5, pp. 901–931 (1989).CrossRefGoogle Scholar
  15. 15.
    J.L. Crowley and Y. Demazeau, Principles and Techniques for Sensor Data Fusion, in Signal Processing, special issue on Intelligent Systems for Signal and Image Understanding, V. Roberto ed., Elsevier Science Publishers, Vol.32, No.1-2, pp. 5–27 (1993).Google Scholar
  16. 16.
    E. Dickmanns, An Integrated Approach to Feature Based Dynamic Vision, Proceedings of the International Conference on Computer Vision and Pattern Recognition, Ann Arbor, MI (1988).Google Scholar
  17. 17.
    R.S. Engelmore and A.J. Morgan eds., Blackboard Systems, Addison Wesley, Wokingham, UK (1988).Google Scholar
  18. 18.
    F. Hayes-Roth, D.A. Waterman, and D.B. Lenat, Principles of Pattern-Directed Inference Systems, in Pattern-Directed Inference Systems, D.A. Waterman and F. Hayes-Roth eds., Academic Press, New York, NY, pp. 577–601 (1978).Google Scholar
  19. 19.
    G. Agha, Actors: a Model of Concurrent Computation in Distributed Systems, MIT Press, Cambridge, MA (1986).Google Scholar
  20. 20.
    C. Hewitt and J. Inman, DAI Betwixt and Between: from “Intelligent Agents” to Open Systems Science, IEEE Transactions on Systems, Man, and Cybernetics, Vol.21, No.6, pp. 1409–1419 (1991).CrossRefGoogle Scholar
  21. 21.
    A. Pentland, Perceptual Organization and the Representation of Natural Form, Artificial Intelligence, Vol.28, pp. 293–331 (1986).CrossRefGoogle Scholar
  22. 22.
    L.G. Shapiro and R.M. Haralick, Structural Descriptions and Inexact Matching, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.3, No.5, pp. 504–519 (1981).PubMedCrossRefGoogle Scholar
  23. 23.
    J. Pearl, Probabilistic Reasoning in Intelligent Systems, Morgan Kaufmann, San Mateo, CA (1988).Google Scholar
  24. 24.
    R. Luccio, Gestalt Problems in Cognitive Psychology: Field Theory, Invariance and Auto-Organisation, in Intelligent Perceptual Systems, V. Roberto ed., Lecture Notes in AI, Springer-Verlag, Berlin, D, Vol.745, pp. 2–19 (1993).CrossRefGoogle Scholar
  25. 25.
    K.S. Fu, Syntactic Pattern Recognition and Applications, Prentice Hall, Englewood Cliffs, NY (1982).Google Scholar
  26. 26.
    Y. Aloimonos, I. Weiss, and A. Bandyopadhyay, Active Vision, Proceedings of the First IEEE Conference on Computer Vision, pp. 35-54 (1987).Google Scholar
  27. 27.
    K. Bowyer and C.R. Dyer, Aspect Graphs: an Introduction and Survey of Recent Results, International Journal of Imaging Systems and Technology, John Wiley & Sons Ltd, Vol.2, pp. 315–328 (1990).CrossRefGoogle Scholar
  28. 28.
    R. Quillian, Semantic Memory, in Semantic Information Processing, M. Minsky ed., MIT Press, Cambridge, MA (1968).Google Scholar
  29. 29.
    R.J. Brachman, What IS-A Is and Isn’t: An Analysis of Taxonomic Links in Semantic Networks, IEEE Computer, Vol.16, No.10, pp. 30–36 (1983).CrossRefGoogle Scholar
  30. 30.
    M. Minsky, A Framework for Representing Knowledge, in The Psychology of Computer Vision, P.H. Winston ed., McGraw Hill, New York, NY, pp. 211–277 (1985).Google Scholar
  31. 31.
    V. Roberto, Perceptual and Conceptual Representations in a Geophysical Image-Understanding System, in Proceedings of the 6th International Conference on Image Analysis and Processing, V. Cantoni, M. Ferretti, S. Levialdi, R. Negrini, and R. Stefanelli eds., World Scientific Publishing Ltd, Singapore, pp. 713–720 (1992).Google Scholar
  32. 32.
    D.G. Bobrow and T. Winograd, An Overview of KRL, a Knowledge Representation Language, Cognitive Science, Vol.1, No.1, pp. 3–46 (1977).CrossRefGoogle Scholar
  33. 33.
    R. Fikes and T. Kehler, The Role of Frame-Based Representation in Reasoning, Communications of the ACM, Vol.28, No.9, pp. 904–920 (1985).CrossRefGoogle Scholar
  34. 34.
    R.J. Brachman and J.G. Schmölze, An Overview of the KL-ONE Knowledge Representation System, Cognitive Science, Vol.9, pp. 171–216 (1985).CrossRefGoogle Scholar
  35. 35.
    E. Ardizzone, S. Gaglio, and F. Sorbello, Geometric and Conceptual Knowledge Representation within a Generative Model of Visual Perception, Journal of Intelligent and Robotic Systems, Kluwer Academic Publishers, Vol.2, pp. 381–409 (1989).CrossRefGoogle Scholar
  36. 36.
    L. Zadeh, Fuzzy Sets and Systems, Elsevier, Amsterdam, NL (1983).Google Scholar
  37. 37.
    A. Deliyanni and R.A. Kowalski, Logic and Semantic Networks, Communications of the ACM, Vol.22, No.3, pp. 184–192 (1979).CrossRefGoogle Scholar
  38. 38.
    P.J. Hayes, The Logic of Frames, in Frame Conceptions and Text Understanding, D. Metzing, W. De Gruyter and Co. ed., Berlin, D, pp. 46-61 (1979).Google Scholar
  39. 39.
    W. Wahlster, E. Andrè, W. Graf, and T. Rist, Knowledge-Based Media Coordination in Intelligent User Interfaces, in Trends in Artificial Intelligence, E. Ardizzone, S. Gaglio, and F. Sorbello eds., Springer-Verlag, Berlin, D, pp. 2–16 (1991).Google Scholar
  40. 40.
    S.K. Chang, Principles of Pictorial Information System Design, Prentice Hall, Englewood Cliffs, NY (1989).Google Scholar
  41. 41.
    J.R.J. Shirra, G. Bosch, C.K. Sung, and G. Zimmermann, From Image Sequences to Natural Language: A First Step Toward Automatic Perception and Description of Motions, Applied Artificial Intelligence, Vol.1, pp. 287–305 (1987).CrossRefGoogle Scholar
  42. 42.
    V. Roberto and C. Chiaruttini, Seismic Signal Understanding: a Knowledge-Based Recognition System, IEEE Transactions on Signal Processing, Vol.40, No.7, pp. 1787–1806 (1992).CrossRefGoogle Scholar
  43. 43.
    R.A. Brooks, Model-Based Three-Dimensional Interpretations of Two-Dimensional Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.5, No.2, pp. 140–150 (1983).PubMedCrossRefGoogle Scholar
  44. 44.
    D.M. McKeown, W.A. Harvey, and J. McDermott, Rule-Based Interpretation of Aerial Imagery, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.7, No.5, pp. 570–585 (1985).PubMedCrossRefGoogle Scholar
  45. 45.
    V. Roberto, Knowledge-Based Understanding of Signals: an Introduction, in Signal Processing, special issue on Intelligent Systems for Signal and Image Understanding, V. Roberto ed., Vol.32, No. 1-2, pp. 5–27 (1993).Google Scholar
  46. 46.
    M. Nagao, T. Matsuyama, and H. Mori, Structural Analysis of Complex Aerial Photographs, in Blackboard Systems, R.S. Engelmore and A.J. Morgan eds., Addison Wesley Publishers Ltd, Wokingham, UK, pp. 219–230 (1988).Google Scholar
  47. 47.
    P.N. Johnson-Laird, Semantic Primitives Or Meaning Postulates: Mental Models Or Propositional Representations?, in Computational Models of Natural Language Processing, B. Bara and G. Guida eds., Elsevier, Amsterdam, NL, pp. 227–243 (1984).Google Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Vito Roberto
    • 1
  1. 1.Dipartimento di InformaticaUniversità di UdineUdineItaly

Personalised recommendations