Probabilistic reasoning in high-level vision

High-level vision is concerned with constructing a model of the visual world and making use of this knowledge for later recognition. In this paper, we develop a general framework for representing uncertain knowledge in high-level vision. Starting from a probabilistic network representation, we develop a structure for presenting visual knowledge, and techniques for probability propagation, parameter learning and structural improvement. This framework provides an adequate basis for representing uncertain knowledge in computer vision, especially in complex natural environments. It has been tested in a realistic problem in cndoscopy, performing image interpretation with good results. We consider that it can be applied in other domains, providing a coherent basis for developing knowledge-based vision systems.

[1]  John P. McDermott,et al.  Rule-Based Interpretation of Aerial Imagery , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Alan K. Mackworth.  Adequacy Criteria for Visual Knowledge Representation , 1987 .

[3]  Peter Burger,et al.  Differential algorithm for the determination of shape from shading using a point light source , 1992, Image Vis. Comput..

[4]  Judea Pearl,et al.  On Evidential Reasoning in a Hierarchy of Hypotheses , 1990, Artif. Intell..

[5]  John Mark Agosta.  The structure of bayes networks for visual recognition , 1988, Conference on Uncertainty in Artificial Intelligence.

[6]  Leonard P. Wesley.  Evidential knowledge-based computer vision , 1986 .

[7]  David J. Spiegelhalter,et al.  Probabilistic Reasoning in Predictive Expert Systems , 1985, UAI.

[8]  David J. Spiegelhalter,et al.  A statistical view of uncertainty in expert systems , 1986 .

[9]  Gregory F. Cooper,et al.  The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks , 1990, Artif. Intell..

[10]  Keung-Chi Ng,et al.  Uncertainty management in expert systems , 1990, IEEE Expert.

[11]  Succar Les,et al.  Probabilistic reasoning in knowledge-based vision systems. , 1991 .

[12]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[13]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[14]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[15]  Jerome A. Feldman,et al.  A functional model of vision and space , 1987 .

[16]  Christopher M. Brown,et al.  Where to Look Next Using a Bayes Net: Incorporating Geometric Relations , 1992, ECCV.

[17]  大田 友一,et al.  Knowledge-based interpretation of outdoor natural color scenes , 1985 .

[18]  David J. Spiegelhalter,et al.  Sequential updating of conditional probabilities on directed graphical structures , 1990, Networks.

[19]  W. A. Perkins,et al.  Rule-Based Interpreting Of Aerial Photographs Using The Lockheed Expert System , 1986 .

[20]  Thomas O. Binford,et al.  Survey of Model-Based Image Analysis Systems , 1982 .

[21]  Ramesh C. Jain,et al.  Knowledge representation and control in computer vision systems , 1988, IEEE Expert.

[22]  Duncan Fyfe Gillies,et al.  Handling Uncertainty in Knowledge-Based Computer Vision , 1991, ECSQARU.