This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Embedding Gestalt Laws in Markov Random Fields
November 1999 (vol. 21 no. 11)
pp. 1170-1187

Abstract—The goal of this paper is to study a mathematical framework of 2D object shape modeling and learning for middle level vision problems, such as image segmentation and perceptual organization. For this purpose, we pursue generic shape models which characterize the most common features of 2D object shapes. In this paper, shape models are learned from observed natural shapes based on a minimax entropy learning theory [31], [32]. The learned shape models are Gibbs distributions defined on Markov random fields (MRFs). The neighborhood structures of these MRFs correspond to Gestalt laws—colinearity, cocircularity, proximity, parallelism, and symmetry. Thus, both contour-based and region-based features are accounted for. Stochastic Markov chain Monte Carlo (MCMC) algorithms are proposed for learning and model verification. Furthermore, this paper provides a quantitative measure for the so-called nonaccidental statistics and, thus, justifies some empirical observations of Gestalt psychology by information theory. Our experiments also demonstrate that global shape properties can arise from interactions of local features.

[1] R. Balboa and N.M. Grzywacz, “Power Spectra of Natural Underwater Images and Possible Implications for Vision,” preprint, Smith-Kettlewell Eye Research Inst., 1998.
[2] F.L. Bookstein, “Size and Shape Spaces for Landmark Data in Two Dimensions,” Statistical Science, vol. 1, no. 2, pp. 181-242, 1986.
[3] C.A. Burbeck and S.M. Pizer, “Object Representation by Cores: Identifying and Representing Primitive Spatial Regions,” Vision Research, vol. 35, no. 13, pp. 1,917-1,930, 1995.
[4] A. Chakraborty, L.H. Staib, and J.S. Duncan, "Deformable boundary finding influenced by region homogeneity," Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),Seattle, pp. 624-627, June 1994.
[5] S.J. Dickinson, A.P. Pentland, and A. Rosenfeld, “From Volumes to Views: An Approach to 3D Object Recognition,” CVGIP: Image Understanding, vol. 55, no. 2, pp. 130-154, Mar. 1992.
[6] I.L. Dryden and K.V. Mardia, Statistical Shape Analysis. Wiley, 1998.
[7] U. Grenander, General Pattern Theory. Oxford Univ. Press, 1993.
[8] Y.S. Chow, U. Grenander, and D.M. Keenan, HANDS. A Pattern-Theoretic Study Of Biological Shapes.New York: Springer-Verlag, 1991.
[9] H. Helmholtz, Treatise on Physiological Optics. New York: Dover, 1962 (first published in 1867).
[10] J.E. Hochberg, “Effects of the Gestalt Revolution: The Cornell Symposium on Perception,” Psychological Review, vol. 64, no. 2, pp. 73-84, 1957.
[11] D.W. Jacobs, Recognizing 3D Objects Using 2D Images, unpublished PhD dissertation, Dept. of Electrical Eng. and Computer Science, Massachusetts Inst. of Tech nology, 1992.
[12] E.T. Jaynes, “Information Theory and Statistical Mechanics,” Physical Review, vol. 106, pp. 620-630, 1957.
[13] G. Kanizsa, Organization in Vision. New York: Praeger, 1979.
[14] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. Int'l Conf. Computer Vision, London, 1987.
[15] D.G. Kendall, “A Survey of the Statistical Theory of Shape,” Statistical Science, vol. 4, no. 2, pp. 87-120, 1989.
[16] D. Keren,D. Cooper,, and J. Subrahmonia,“Describing complicated objects by implicit polynomials,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 38-53, 1994.
[17] K. Koffka, Principles of Gestalt Psychology. New York: Harcourt, Brace and Company 1935.
[18] I. Kovacs and B. Julesz, “Perceptual Sensitivity Maps within Globally Defined Visual Shapes,” Nature, vol. 371, pp. 644-646, 1996.
[19] T.S. Lee, D.B. Mumford, S.C. Zhu, and V. Lamme, “The Role of V1 in Shape Representation,” Computational Neuroscience, K. Bower, ed., New York: Plenum Press, 1997.
[20] M. Leyton, Symmetry, Causality, Mind. Cambridge, Mass.: MIT Press, 1992.
[21] D.G. Lowe, Perceptual Organization and Visual Recognition. Boston: Kluwer Academic, 1985.
[22] D.G. Lowe, “Visual Recognition as Probabilistic Inference from Spatial Relations,” AI and Eye, A. Blake and T. Troscianko, eds., John Wiley&Sons Ltd., 1990.
[23] K.V. Mardia and I.L. Dryden, “Statistical Analysis of Shape Data,” Biometrika, vol. 76, pp. 271-281, 1989.
[24] R. Mohan and R. Nevatia, "Perceptual Organization for Scene Segmentation and Description," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 6, pp. 616-635, June 1992.
[25] D.B. Mumford, “Elastica and Computer Vision,” Algebraic Geometry and Its Applications, C.L. Bajaj, ed., New York: Springer-Verlag, 1994.
[26] A. Pentland,“Perceptual organization and the representation of natural form,” Artificial Intelligence, vol. 28, pp. 293-331, 1986.
[27] L.R. Williams and D.W. Jacobs, “Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience,” Neural Computation, vol. 9, pp. 837-858, 1997.
[28] A.L. Yuille, “Deformable Templates for Face Recognition,” J. Cognitive Neurosciences, vol. 3, no. 1, 1991.
[29] S.C. Zhu and A. Yuille, “Region Competition: Unifying Snakes, Region Growing and Bayes/MDL for Multiband Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp. 884-900, 1996.
[30] S.C. Zhu and A.L. Yuille, “FORMS: A Flexible Object Recognition and Modeling System,” Int'l J. Computer Vision, vol. 20, no. 3, Dec. 1996
[31] S.C. Zhu and D. Mumford, “Prior Learning and Gibbs Reaction-Diffusion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 11, Nov. 1997.
[32] S.C. Zhu, Y.N. Wu, and D. Mumford, “Minimax Entropy Principle and Its Application to Texture Modeling,” Neural Computation, vol. 9, no 8, Nov. 1997.
[33] S.C. Zhu, “Stochastic Computation of Medial Axis in Markov Random Field,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 11, pp. 1,158-1,169, Nov. 1999.
[34] S.C. Zhu, “Embedding Gestalt Laws in Markov Random Fields,” technical report, Dept. of Computer Science, Ohio State Univ., 1998.

Index Terms:
Gestalt laws, perceptual grouping, shape modeling, Markov random field, maximum entropy, shape synthesis, active contour.
Citation:
Song-Chun Zhu, "Embedding Gestalt Laws in Markov Random Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 11, pp. 1170-1187, Nov. 1999, doi:10.1109/34.809110
Usage of this product signifies your acceptance of the Terms of Use.