Panel Summary Image Interpretation and Ambiguities

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.

[1]  Irvin Rock,et al.  The perception of visual angle , 1964 .

[2]  Peter Piela,et al.  Work language analysis and the naming problem , 1993, CACM.

[3]  I Rock,et al.  Size Constancy in Children: A New Interpretation , 1988, Perception.

[4]  Piero Mussio,et al.  Automatic cell count in digital images of liver tissue sections , 1991, [1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium.

[5]  Ryszard S. Michalski,et al.  A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.

[6]  King-Sun Fu,et al.  A distance measure between attributed relational graphs for pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Ladislav Tondl,et al.  Problems of semantics , 1981 .

[8]  Donato Malerba,et al.  Negation as a Specializing Operator , 1993, AI*IA.

[9]  L. Arend,et al.  Simultaneous constancy, lightness, and brightness. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[10]  Donato Malerba,et al.  Automated acquisition of rules for document understanding , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[11]  P. Schönemann.  On artificial intelligence , 1985, Behavioral and Brain Sciences.

[12]  Harry Wechsler,et al.  Active Perception and Robot Vision , 1993, NATO ASI Series.

[13]  Nicolas Helft,et al.  Inductive Generalization: A Logical Framework , 1987, EWSL.

[14]  Lorenza Saitta,et al.  Automated Concept Acquisition in Noisy Environments , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  L. Arend,et al.  Perceived lightness, but not brightness, of achromatic surfaces depends on perceived depth information , 1990, Perception & psychophysics.

[16]  Donato Malerba,et al.  Flexible Matching for Noisy Structural Descriptions , 1991, IJCAI.

[17]  Gheorghe Tecuci,et al.  Learning Based on Conceptual Distance , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  W. Epstein.  Attitudes of judgment and the size-distance invariance hypothesis. , 1963 .

[19]  P. Mussio,et al.  Attributed Parallel Rewriting in Vision , 1992 .

[20]  Stephen E. Palmer,et al.  Perception of partly occluded objects: A microgenetic analysis. , 1992 .

[21]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[22]  I. Rock.  The Logic of Perception , 1983 .

[23]  Michael Brady,et al.  Generating and Generalizing Models of Visual Objects , 1987, Artif. Intell..

[24]  S. Petry,et al.  The Perception of Illusory Contours , 1987 .

[25]  Donato Malerba,et al.  Classification in Noisy Environments Using a Distance Measure Between Structural Symbolic Descriptions , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Afzelius Ba.  Interpretation of electron micrographs. , 1987 .

[27]  Andrew K. C. Wong,et al.  Entropy and Distance of Random Graphs with Application to Structural Pattern Recognition , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Ennio Mingolla,et al.  Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations , 1985 .

[29]  A. S. Gilinsky,et al.  The effect of attitude upon the perception of size. , 1955, The American journal of psychology.

[30]  J. Gibson.  The perception of the visual world , 1951 .

[31]  Stephen Jose Hanson,et al.  CONCEPTUAL CLUSTERING AND CATEGORIZATION , 1990 .

[32]  Ryszard S. Michalski,et al.  The AQ15 Inductive Learning System: An Overview and Experiments , 1986 .

[33]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[34]  S. Vere.  Induction of concepts in the predicate calculus , 1975, IJCAI 1975.

[35]  T. Natsoulas,et al.  The tunnel effect, Gibson's perception theory, and reflective seeing , 1992, Psychological research.

[36]  Thomas Natsoulas.  Reflective Seeing: An Exploration in the Company of Edmund Husserl and James J. Gibson , 1990 .