Panel Summary Image Interpretation and Ambiguities

  • Piero Mussio
  • Nicola Bruno
  • Floriana Esposito


The goal of the panel is to discuss if ambiguity can be a means for performing cognitive tasks. This position contrasts with the traditional view which considers ambiguous situations as pathological ones to be avoided or recovered as soon as they arise. Evidence exists that the human visual system attempts to process its inputs according to two different representations, the distal and the proximal one. N. Bruno as a cognitive scientist introduces the argument and speculates on the cognitive function served by the proximal interpretation. On the other side, P. Mussio explores - from the point of view of an image interpreter - some situations in which scientists and technicians exploit ambiguous image interpretations to better understand the situation under study. Programs - developed to help them in these interpretation activities-explicitly create and exploit ambiguous descriptions of a same image. However, in many cases ambiguity is still a problem. F. Esposito as an AI scientist explores how to face the intrinsic ambiguity in learning models of visual objects.


Visual Angle Image Interpretation Human Visual System Noisy Environment Representation Language 
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.
    J.J. Gibson, The perception of the visual world, Hughton Mifflin, Boston, MA (1950).Google Scholar
  2. 2.
    I. Rock, In defense of unconscious inference, in Stability and constancy in visual perception, W. Epstein ed., Wiley (1977).Google Scholar
  3. 3.
    I. Rock, The logic of perception, Ma: MIT press, Boston, MA (1983).Google Scholar
  4. 4.
    T. Natsoulas, Reflective seeing: an exploration in the company of Edmund Husserl and James J. Gibson, Journal of Phenomenological Psychology, Vol.21, pp. 1–31 (1990).CrossRefGoogle Scholar
  5. 5.
    T. Natsoulas, The tunnel effect, Gibson’s perception theory, and reflective seeing, Psychological Research, Vol.54, pp. 160–174 (1990).CrossRefGoogle Scholar
  6. 6.
    L.E. Arend and R. Goldstein, Simultaneous constancy, lightness, and brightness, Journal of the optical society of America A, Vol.4, pp. 2281–2285 (1987).CrossRefGoogle Scholar
  7. 7.
    J. Schirillo, A. Reeves, and L. Arend, Perceived lightness, but not brightness, of achromatic surfaces depends on perceived depth information, Perception and Psychophysics, Vol.48, pp. 82–90 (1990).PubMedCrossRefGoogle Scholar
  8. 8.
    W. Epstein, Attitudes of judgment and the size-distance invariance hypothesis, Journal of Experimental Psychology, Vol.66, pp. 78–83 (1963).CrossRefGoogle Scholar
  9. 9.
    A.S. Gilinsky, The effect of attitude upon the perception of size, American Journal of Psychology, Vol.68, pp. 173–192 (1955).PubMedCrossRefGoogle Scholar
  10. 10.
    J. Shallo and I. Rock, Size constancy in children: A new interpretation, Perception, Vol.17, pp. 803–814 (1988).PubMedCrossRefGoogle Scholar
  11. 11.
    I. Rock and W. McDermott, The perception of visual angle, Acta Psychologica, Vol.22, pp. 119–134 (1964).CrossRefGoogle Scholar
  12. 12.
    N. Bruno and N. Gerbino, L’occlusione dinamica: implicazioni per i modelli di visione artificiale, in I sensi dell’automa, G. Adorni, W. Gerbino, and V. Roberto, Edizioni Lint, Trieste, I (1992).Google Scholar
  13. 13.
    D. Marr, Vision, Freeman, San Francisco, CA (1982).Google Scholar
  14. 14.
    S. Grossberg and E. Mingolla, Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations, Perception and Psychophysics, Vol.38, pp. 141–171 (1985).PubMedCrossRefGoogle Scholar
  15. 15.
    N. Bruno and N. Gerbino, Amodal completion and illusory figures: An information-processing analysis, in The perception of illusory contours, S. Petry and G. Meyer, Springer, New York, NY (1987).Google Scholar
  16. 16.
    W. Gerbino and D. Salmaso, Un’analisi processuale del completamento amodale, Giornale Italiano di Psicologia, Vol.12, pp. 97–121 (1985).Google Scholar
  17. 17.
    A.B. Sekuler and S.E. Palmer, Perception of partly occluded objects: a microgenetic analysis, Journal of Experimental Psychology: General, Vol.121, pp. 95–111 (1992).CrossRefGoogle Scholar
  18. 18.
    J.J. Gibson, The ecological approach to visual perception, Hughton Mifflin, Boston, MA (1979).Google Scholar
  19. 19.
    A.P. Witkin and J.M. Tenenbaum, On perceptual organisation, in From pixels to predicates, Pentland ed., Ablex Publishing, pp. 149-169 (1986).Google Scholar
  20. 20.
    P. Mussio and M. Protti, Attributed parallel rewriting in vision, in Active Perception and Robot Vision, NATO ASI Series, Springer-Verlag, Berlin, D (1993).Google Scholar
  21. 21.
    M.A. Arbib and A.R. Hanson, Vision in perspective, in Vision, Brain and Cooperative Computation, Arbib and Hanson eds., MIT Press, pp. 1-83 (1987).Google Scholar
  22. 22.
    P. Mussio, M. Pietrogrande, P. Bottom, M. Dell’Oca, E. Arosio, E. Sartirana, M.R. Finanzon, and N. Dioguardi, Automatic cell count in digital images of liver tissue sections, Proc. 4th IEEE Symposium on Computer-Based Medical Systems, IEEE Computer Society Press, pp. 153-160 (1991).Google Scholar
  23. 23.
    L. Tondi, Problems of Semantics, Reidel Publishing Company, Dordrecht, D (1981).CrossRefGoogle Scholar
  24. 24.
    B.A. Afzelius, Interpretation of Electron Micrographs, Scanning Microsc. 1, pp. 1157–1165 (1987).PubMedGoogle Scholar
  25. 25.
    N. Bianchi, G. Rubbia, R. Di Lernia, and P. Mussio, Automatic discovery of emergent patterns in citological images, to appear in Journal of Hystochemistry (1993).Google Scholar
  26. 26.
    B. Katzemberg and P. Piola, Work Language Analysis and the naming problem, Comm. Acm, Vol.36, No. 4, pp. 86–92 (1993).CrossRefGoogle Scholar
  27. 27.
    J.H. Connell and M. Brady, Generating and Generalizing Models of Visual Objects, Artificial Intelligence, No.31, pp. 159–183 (1987).CrossRefGoogle Scholar
  28. 28.
    R.S. Michalski, A theory and methodology of inductive learning, in Machine Learning, an Artificial Intelligence Approach, R.S. Michalski, J.G. Carbonell, and T. Mitchell eds., Tioga, Palo Alto, CA, pp. 83–134 (1983).Google Scholar
  29. 29.
    S.J. Hanson, Conceptual Clustering and categorization, in Machine Learning: an Artificial Intelligence Approach, Y. Kodratoff and R.S. Michalski eds., Vol. III. Morgan Kaufmann, San Mateo, CA, pp. 235–268 (1990).Google Scholar
  30. 30.
    F. Bergadano, A. Giordana, and L. Saitta, Automated Concept Acquisition in noisy environments, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, pp. 555–578 (1988).CrossRefGoogle Scholar
  31. 31.
    J.R. Quinlan, Induction of Decision Trees, Machine Learning, No. 1, pp. 81–106 (1986).Google Scholar
  32. 32.
    A. Sanfeliu and K.S. Fu, A distance measure between attributed relational graphs for Pattern Recognition, IEEE Transactions on Systems, Man and Cybernetics, Vol.13, pp. 353–362 (1983).CrossRefGoogle Scholar
  33. 33.
    A.K.C. Wong and M. You, Entropy and Distance of Random Graphs with Application to Structural Pattern Recognition, IEEE Transactions on Pattern Analysis and Machine intelligence, Vol.8, pp. 599–609 (1985).CrossRefGoogle Scholar
  34. 34.
    R.S. Michalski, I. Mozetic, J. Hong, and N. Lavrac, The AQ15 inductive Learning system: an overview and experiments, Int. Rep. Dept. of Computer Science, University of Illinois, Urbana, IL (1986).Google Scholar
  35. 35.
    Y. Kodratoff and G. Tecuci, Learning based on conceptual distance, IEEE Transactions on pattern Analysis and Machine Intelligence, Vol. 10, pp. 897–909 (1988).CrossRefGoogle Scholar
  36. 36.
    J. Nicolas, J. Lebbe, and R. Vignes, From Knowledge to similarity, in Symbolic-Numeric Data Analysis and Learning, E. Diday and Y. Lechevallier eds., Nova Science Pub., New York, NY, pp. 585–597 (1991).Google Scholar
  37. 37.
    F. Esposito, D. Malerba, and G. Semeraro, Classification in noisy environments using a Distance Measure between structural symbolic descriptions, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.14, No.3, pp. 390–402 (1992).CrossRefGoogle Scholar
  38. 38.
    F. Esposito, D. Malerba, and G. Semeraro, Flexible Matching for noisy structural descriptions, in Proc. of 12th Int. Conf. on Artificial Intelligence, Morgan Kaufmann, Sidney, AU, pp. 658–664 (1991).Google Scholar
  39. 39.
    G.D. Plotkin, A Note on Inductive Generalization, in Machine Intelligence 5, B. Meltzer and D. Michie eds., Edinburgh University Press, pp. 153-163 (1970).Google Scholar
  40. 40.
    S.A. Vere, Induction of Concepts in Predicate Calculus, Proc. IJCAI, Tblisi, USSR, pp. 281–287 (1975).Google Scholar
  41. 41.
    N. Helft, Inductive Generalization: a logical framework, in Progress in Machine Learning, Proc. EWSL 87, Bled, YU (1987).Google Scholar
  42. 42.
    D. Haussler, Learning Conjunctive Concepts in Structural Domains, Machine Learning, Vol.4, pp. 7–40 (1989).Google Scholar
  43. 43.
    F. Esposito, D. Malerba, and G. Semeraro, Negation as a Specializing Operator, in Advances in Artificial Intelligence, P. Torasso ed., Lectures Notes in AI, No. 728, Springer-Verlag, pp. 166-177 (1993).Google Scholar
  44. 44.
    F. Esposito, D. Malerba, and G. Semeraro, Automated Acquisition of Rules for Document Understanding, Proc. of ICDAR93, Tsukuba, J, pp. 650-654 (1993).Google Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Piero Mussio
    • 1
  • Nicola Bruno
    • 2
  • Floriana Esposito
    • 3
  1. 1.Dipartimento di Scienze dell’InformazioneUniversità degli Studi “La Sapienza”RomaItaly
  2. 2.Dipartimento di PsicologiaUniversità di TriesteTriesteItaly
  3. 3.Dipartimento di InformaticaUniversità di BariBariItaly

Personalised recommendations