This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata
May 2000 (vol. 22 no. 5)
pp. 504-525

Abstract—Perceptual organization offers an elegant framework to group low-level features that are likely to come from a single object. We offer a novel strategy to adapt this grouping process to objects in a domain. Given a set of training images of objects in context, the associated learning process decides on the relative importance of the basic salient relationships such as proximity, parallelness, continuity, junctions, and common region toward segregating the objects from the background. The parameters of the grouping process are cast as probabilistic specifications of Bayesian networks that need to be learned. This learning is accomplished using a team of stochastic automata in an N-player cooperative game framework. The grouping process, which is based on graph partitioning is, able to form large groups from relationships defined over a small set of primitives and is fast. We statistically demonstrate the robust performance of the grouping and the learning frameworks on a variety of real images. Among the interesting conclusions are the significant role of photometric attributes in grouping and the ability to form large salient groups from a set of local relations, each defined over a small number of primitives.

[1] D. Clemens and D. Jacobs, "Space and time bounds on model indexing," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 1,007-1,018, 1991.
[2] W.E.L. Grimson, "The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 920-935, Sept. 1991.
[3] I. Rock and S. Palmer, “The Legacy of Gesalt Psychology,” Scientific Am., pp. 84-90, Dec. 1990.
[4] D.G. Lowe, “Three-Dimensional Object Recognition from Single Two-Dimensional Images,” Artificial Intelligence, vol. 31, pp. 355-395, 1987.
[5] A. Etemadi, J.-P. Schmidt, G. Matas, J. Illingworth, and J. Kittler, “Low-Level Grouping of Straight Line Segments,” Proc. British Machine Vision Conf., pp. 119-126, 1991.
[6] D.W. Jacobs, "Robust and Efficient Detection of Salient Convex Groups," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp. 23-37, Jan. 1996.
[7] G. Roth and M.D. Levine, “Geometric Primitive Extraction Using a Genetic Algorithm,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 1, no. 9, pp. 901-905, Sept. 1994.
[8] R. Mohan and R. Nevatia, “Using Perceptual Organization to Extract 3-D Structures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 11, pp. 1,121-1,139, Nov. 1989.
[9] M.L. Thathachar and P.S. Sastry, “Learning Optimal Discriminant Functions Through a Cooperative Game of Automata,” IEEE Trans. Systems, Man, and Cybernetics, vol. 17, pp. 73-85, Jan. 1987.
[10] M.S. Lew, T.S. Huang, and K. Wong, “Learning and Feature Selection in Stereo Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 869-881, Sept. 1994.
[11] H. Greenspan, R. Goodman, R. Chellappa, and C.H. Anderson, “Learning Texture Discrimination Rules in a Multiresolution System,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 894-900, Sept. 1994.
[12] K. Cho and S.M. Dunn, “Learning Shape Classes,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 882-887, Sept. 1994.
[13] B. Bhanu, S. Lee, and J. Ming, “Adaptive Image Segmentation Using a Genetic Algorithm,” IEEE Trans. Systems, Man, and Cybernetics, vol. 25, pp. 1,543-1,567, Dec. 1995.
[14] A.R. Pope and D.G. Lowe, “Learning Probabilistic Appearance Models for Object Recognition,” Early Visual Learning, S.K. Nayar and T. Poggio, eds., pp. 67-98, Oxford Univ. Press, 1996.
[15] B. Draper, “Modelling Object Recognition as a Markov Decision Process,” Proc. Int'l Conf. Pattern Recognition, vol. D, pp. 95-99, 1996.
[16] S. Houzelle, T.M. Strat, P. Fua, and M.A. Fischler, “Using Contextual Information to Set Control Parameter of a Vision Process,” Proc. Int'l Conf. Pattern Recognition—Part A, pp. 830-832, 1994.
[17] V. Murino, G.L. Foresti, and C.S. Regazzonni, “A Distributed Probabilistic System for Adaptive Regulation of Image Processing Parameters,” IEEE Trans. Systems, Man, and Cybernetics—Part B: Cybernetics, vol. 26, pp. 1-20, Feb. 1996.
[18] V. Murino, G.L. Foresti, and C.S. Regazzoni, “A Belief Based Approach for Adaptive Image Processing,” Int'l J. Pattern Recognition and Artificial Intelligence, vol. 11, pp. 359-392, May 1997.
[19] J. Peng and B. Bhanu, “Closed Loop Object Recognition Using Reinforcement Learning,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 139-154, Feb. 1998.
[20] Z. Wu and R. Leahy, “An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1,101-1,113, Nov. 1993.
[21] G. Guy and G. Medioni, “Inferring Global Perceptual Contours from Local Features,” Int'l J. Computer Vision, vol. 20, pp. 113-133, 1996.
[22] J. Shi and J. Malik, “Normalized Cuts and Image Segmenation,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 731-737, June 1997.
[23] A. Amir and M. Lindenbaum, “A Generic Grouping Algorithm and Its Quantitative Analysis,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp. 168-185, Feb. 1998.
[24] A. Sha'ashua and S. Ullman, “Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network,” Proc. Int'l Conf. Computer Vision, pp. 321-327, 1988.
[25] J. Elder and S. Zucker, “Computing Contour Closure,” Proc. European Conf. Computer Vision, pp. 399-412, 1996.
[26] L. Williams and A.R. Hanson, “Perceptual Completion of Occluded Surfaces,” Computer Vision and Image Understanding, vol. 64, pp. 1-20, July 1996.
[27] S. Casadei and S.K. Mitter, “Hierarchical Image Segmentation-Detection of Regular Curves in a Vector Graph,” Int'l J. Computer Vision, vol. 27, no. 3, 1998.
[28] S. Sarkar and K.L. Boyer, "Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 3, pp. 256-274, Mar. 1993. Special Section on Probabilistic Reasoning.
[29] S. Sarkar and K.L. Boyer, “A Computational Structure for Preattentive Perceptual Organization: Graphical Enumeration and Voting Methods,” IEEE Trans. Systems, Man, and Cybernetics, vol. 24, pp. 246-267, Feb. 1994.
[30] L. Herault and R. Horaud, “Figure Ground Discrimination: A Combinatorial Optimization Method,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 899-914, Sept. 1993.
[31] J.D. McCafferty, Human and Machine Vision: Computing Perceptual Organization. West Sussex, England: Ellis Horwood, 1990.
[32] S. Sarkar and K.L. Boyer, “Quantitative Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 478-483, June 1996.
[33] S. Sarkar and K.L. Boyer, “Quantitative Measure of Change Based on Feature Organization: Eigenvalues and Eigenvectors,” Computer Vision and Image Understanding, vol. 71, pp. 110-136, July 1998.
[34] L.S. Shapiro and J.M. Brady, “Feature-Based Correspondence: An Eigenvector Approach,” Image and Vision Computing, vol. 10, pp. 283-288, 1992.
[35] K. Sengupta and K.L. Boyer, “Organizing Large Structural Modelbases,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 4, pp. 321-332, Apr. 1995.
[36] E. Ihler, D. Wagner, and F. Wagner, “Modeling Hypergraphs by Graphs with the Same Mincut Properties,” Information Processing Letters, vol. 45, pp. 171-175, Mar. 1993.
[37] K.L. Boyer, D.M. Wuescher, and S. Sarkar, “Dynamic Edge Warping: An Experimental System for Recovering Disparity Maps in Weakly Constrained Systems,” IEEE Trans. Systems, Man, and Cybernetics, vol. 21, pp. 143-158, Jan. 1991.
[38] J. Pearl, Probabilistic Reasoning in Intelligent Systems. San Mateo, Calif.: Morgan Kaufman, 1988.
[39] R.A. Horn and C.R. Johnson, Matrix Analysis. Cambridge Univ. Press, 1990.
[40] M. Fiedler, “Algebraic Connectivity of Graphs,” Czechoslovakian Math. J., vol. 23, pp. 298-305, 1973.
[41] A. Pothen, H. Simon, and K. Liou, "Partitioning Sparse Matrices with Eigenvectors of Graphs," SIAM J. Matrix Analysis and Application, vol. 11, pp. 430-352, July 1990.
[42] M. Fiedler, “A Property of Eigenvectors of Nonnegative Symmetric Matrices and Its Application to Graph Theory,” Czechoslovakian Math. J. vol. 25, pp. 619-637, 1975.
[43] S.Z. Li, “Parameter Estimation for Optimal Object Recognition: Theory and Application,” Int'l J. Computer Vision, vol. 21, pp. 207-222, Feb. 1997.
[44] M. Pelillo and M. Refice, “Learning Compatibility Coefficients for Relaxation Labelling Processes,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 933-945, Sept. 1994.
[45] K.S. Narendra and M.L. Thathachar, Learning Automata: An Introduction. Prentice Hall, 1989.
[46] S. Borra and S. Sarkar, “A Framework for Performance Characterization of Intermediate-Level Grouping Modules,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 11, pp. 1,306-1,312, Nov. 1997.
[47] S. Sarkar, “Learning to Form Large Groups of Salient Image Features,” IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 780-786, June 1998.

Index Terms:
Perceptual organization, learning in vision, learning automata, Bayesian networks, feature grouping, object recognition, figure ground segmentation.
Citation:
Sudeep Sarkar, Padmanabhan Soundararajan, "Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 5, pp. 504-525, May 2000, doi:10.1109/34.857006
Usage of this product signifies your acceptance of the Terms of Use.