Ecological Statistics of Contour Grouping
The Gestalt laws of perceptual organization were originally conceived as qualitative principles, intrinsic to the brain. In this paper, we develop quantitative models for these laws based upon the statistics of natural images. In particular, we study the laws of proximity, good continuation and similarity as they relate to the perceptual organization of contours. We measure the statistical power of each, and show how their approximate independence leads to a Bayesian factorial model for contour inference. We showho wthese local cues can be combined with global cues such as closure, simplicity and completeness, and with prior object knowledge, for the inference of global contours from natural images. Our model is generative, allowing contours to be synthesized for visualization and psychophysics.
KeywordsNatural Image Global Constraint Perceptual Organization Good Continuation Likelihood Distribution
Unable to display preview. Download preview PDF.
- 1.M. Wertheimer, “Laws of organization in perceptual forms,” in A sourcebook of Gestalt Psychology, W. D. Ellis, Ed., pp. 71–88. Routledge and Kegan Paul, London, 1938.Google Scholar
- 3.J. H. Elder and S. W. Zucker, “Computing contour closure,” in Proceedings of the 4th European Conference on Computer Vision, NewYork, 1996, pp. 399–412, Springer Verlag.Google Scholar
- 6.J. H. Elder and R. M. Goldberg, “Ecological statistics of Gestalt laws for the perceptual organization of contours,” Journal of Vision, vol. 2, no. 4, pp. 324–353, 2002, http://journalofvision.org/2/4/5/, DOI 10.1167/2.4.5. CrossRefGoogle Scholar
- 11.J. H. Elder and A. Krupnik, “Contour grouping with strong prior models,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, December 2001, IEEE Computer Society, pp. 414–421, IEEE Computer Society Press.Google Scholar