Qualitative probabilities for image interpretation

Two basic problems in image interpretation are: a) determining which interpretations are the most plausible amongst many possibilities; and b) controlling the search for plausible interpretations. We address these issues using a Bayesian approach, with the plausibility ordering and search pruning based on the posterior probabilities of interpretations. However, due to the need for detailed quantitative prior probabilities and the need to evaluate complex integrals over various conditional distributions, a full Bayesian approach is currently impractical except in tightly constrained domains. To circumvent these difficulties we introduce the notion of qualitative probabilistic analysis. In particular, given spatial and contrast resolution parameters, we consider only the asymptotic order of the posterior probability for any interpretation as these resolutions are made finer. We introduce this approach for a simple card-world domain, and present computational results for blocks-world images.

[1]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[2]  Eric Saund,et al.  Perceptual organization of occluding contours generated by opaque surfaces , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[3]  Eric Saund.  Perceptual Organization of Occluding Contours of Opaque Surfaces , 1999, Comput. Vis. Image Underst..

[4]  Azriel Rosenfeld,et al.  From volumes to views: An approach to 3-D object recognition , 1992, CVGIP Image Underst..

[5]  David W. Jacobs.  Robust and efficient detection of convex groups , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  W. Richards,et al.  Model structure and reliable inference , 1996 .

[7]  K Nakayama,et al.  Experiencing and perceiving visual surfaces. , 1992, Science.

[8]  Edward H. Adelson,et al.  The perception of shading and reflectance , 1996 .

[9]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[10]  Lance R. Williams,et al.  A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds , 1998, ECCV.

[11]  Allen R. Hanson,et al.  Perceptual Completion of Occluded Surfaces , 1996, Comput. Vis. Image Underst..

[12]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[14]  Thomas O. Binford,et al.  Inferring Surfaces from Images , 1981, Artif. Intell..

[15]  Jacob Feldman,et al.  Regularity‐based Perceptual Grouping , 1997, Comput. Intell..

[16]  Allen R. Hanson,et al.  Perceptual completion of occluded surfaces , 1996, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.