This Article 
 Bibliographic References 
 Add to: 
Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization
March 1993 (vol. 15 no. 3)
pp. 256-274

The formalism of Bayesian networks provides a very elegant solution, in a probabilistic framework, to the problem of integrating top-down and bottom-up visual processes, as well serving as a knowledge base. The formalism is modified to handle spatial data, and thus the application of Bayesian networks is extended to visual processing. The modified form is called the perceptual inference network (PIN). The theoretical background of a PIN is presented, and its viability is demonstrated in the context of perceptual organization. Perceptual organization imparts robustness, efficiency, and a qualitative and holistic nature to vision. Thus far, the approaches to the problem of perceptual organization have been purely bottom up, without much top-down knowledge-base influence, and are therefore entirely dependent on the inputs, which are obviously imperfect. The knowledge base, besides coping with such input imperfection, also makes it possible to integrate multiple organizations and form a composite organization hypothesis. The PIN imparts an active inferential and integrating nature to perceptual organization in an elegant probabilistic framework.

[1] A. Witkin and J. Tenenbaum, "On the role of structure in vision," inHuman and Machine Vision(J. Beck, B. Hope, and A. Rosenfeld, Eds.). New York: Academic, 1983, pp. 481-543.
[2] J. D. McCafferty,Human and Machine Vision: Computing Perceptual Organization. Ellis Horwood: West Sussex, England, 1990.
[3] G. Kanizsa,Organization in Vision. New York: Praeger, 1979.
[4] J. Pearl,Probabilistic Reasoning in Intelligent Systems. San Mateo, CA: Morgan Kaufman, 1988.
[5] D. Marr, VISION:A Computational Investigation into the Human Representation and Processing of Visual Information. San Francisco, CA: W. H. Freeman, 1981.
[6] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[7] D. G. Lowe, "Three-dimensional object recognition from single two-dimensional images,"Artificial Intell., vol. 31, 1987.
[8] N. Ahuja and M. Tuceryan, "Extraction of early perceptual structure in dot patterns: Integrating region, boundary, and component gestalt,"Comput. Vision, Graphics, Image Processing, vol. 48, pp. 304-356, 1989.
[9] S. P. Liou, A. H. Chiu, and R. C. Jain, "A parallel technique for signal level perceptual organization,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, pp. 317-325, Apr. 1991.
[10] M.A. Fischler and R. C. Bolles, "Perceptual organization and curve partitioning,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, no. 1, pp. 100-105, 1986.
[11] P. L. Rosin and G. A. W. West, "Extracting surfaces of revolution by perceptual grouping of ellipses," inIEEE Proc. Comput. Soc. Conf. Comput. Vision Patt. Recogn., 1991, pp. 677-678.
[12] T. Rearick, J. Frawley, and P. Cortopassi, "Using perceptual grouping to recognize and locate partially occluded objects," inIEEE Proc. Comput. Soc. Conf. Comput. Vision Patt. Recogn., 1988, pp. 840-846.
[13] L. Quan and R. Mohr, "Matching perspective images using geometric constraints and perceptual grouping,"Int. Conf. Computer-Vision, Tampa, FL, Dec. 1988, pp. 679-684.
[14] T. R. Reed and H. Wechsler, "Segmentation of textured images and gestalt organization using spatial/spatial-frequency representations,"IEEE Trans. Patt. Anal. Machine Intell., vol. 12, pp. 1-12, Jan. 1990.
[15] L. R. Williams, "Perceptual organization of occluding contours," inProc. Int. Conf. Comput. Vision, 1990, pp. 133-137.
[16] K. Rao and R. Nevatia, "Descriptions of complex objects from incomplete and imperfect data," inProc. DARPA Image Understanding Workshop, 1989, pp. 399-414.
[17] A. P. Pentland, "Perceptual organization and the representation of natural form,"Artificial Intell., vol. 28, no. 3, pp. 293-331, 1986.
[18] M. Nitzberg and D. Mumford, "The 2.1-D sketch," inProc. ICCV 1990.
[19] D. A. Trytten and M. Tuceryan, "Segmentation and grouping of object boundaries using energy minimization," inIEEE Proc. Comput. Soc. Conf. Comput. Vision Patt. Recogn., 1991, pp. 730-731.
[20] M. Boldt, R. Weiss, and E. Riseman, "Token based extraction of straight lines,"IEEE Syst. Man Cybern, vol. 19, no. 6, pp. 1581-1594, Dec. 1989.
[21] J. Dolan and R. Weiss, "Perceptual grouping of curved lines," inProc. SPIE Cambridge, Nov. 1988, pp. 1-9.
[22] D. T. Lawton and C. C. McConnell, "Perceptual organization using interestingness," inProc. 1987 Workshop Spatial Reasoning Multisensor Fusion, 1987, pp. 405-419.
[23] A. Sha'ashua and S. Ullman, "Structural saliency: The detection of globally salient structures using a locally connected network," inProc. Second Int. Conf. Comput. Vision(Tarpon Springs, FL), 1988, pp. 321-327.
[24] R. Mohan and R. Nevatia, "Using perceptual organization to extract 3-D structures,"IEEE Trans. Patt. Anal. Machine Intell., vol. 11, pp. 1121-1139, Nov. 1989.
[25] R. Mohan and R. Nevatia, "Perceptual organization for scene segmentation and description,"IEEE Trans. Patt. Anal. Machine Intell., vol. 14, pp. 616-635, June 1992.
[26] T. O. Binford, T. S. Levitt, and W. B. Mann, "Bayesian inference in model based machine vision," inProc. AAAI Workshop Uncertainty Artificial Intell., 1987, pp. 86-92.
[27] D. M. Chelberg, "Uncertainty in interpretation of range imagery," inProc. Int. Conf. Comput. Vision, 1990, pp. 654-657.
[28] F. V. Jensen, H. I. Christensen, and J. Nielsen, "Bayesian methods for interpretation and control in multi-agent vision systems," inProc. SPIE: Applications Artificial Intell. X; Machine Vision Robotics, Apr. 1992, pp. 536-548.
[29] R. C. Munck-Fairwood, "Recognition of geometric primitives using logic program and probabilistic network reasoning methods," inProc. SPIE: Applications Artificial Intell. X; Machine Vision Robotics, Apr. 1992, pp. 589-600.
[30] R. D. Rimey and C. M. Brown, "Task specific utility in a general Bayes net vision system," inIEEE Proc. Comput. Soc. Conf. Comput. Vision Patt. Recogn., 1992, pp. 142-147.
[31] S. Sarkar and K. L. Boyer, "A highly efficient computational structure for perceptual organization," Tech. Rep. SAMPL-90-06, SAMP-Lab, Dept. Elec. Eng, Ohio St. Univ., Nov. 1990.
[32] C. T. Zahn, "Graph theoretical methods for detecting and describing gestalt clusters,"IEEE Trans. Comput., vol. C-20, pp. 68-86, Jan. 1971.
[33] A. Wong and M. You, "Entropy and distance of random graphs with application to structural pattern recognition,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, pp. 599-609, Sept. 1985.
[34] D. M. Wuescher and K. L. Boyer, "Robust contour decomposition using a constant curvature criterion,"IEEE Trans. Patt. Anal. Machine Intell., vol. 13, pp. 41-51, Jan. 1991.
[35] T.H. Cormen, C.E. Leiserson, and R.L. Rivest,Introduction to Algorithms, McGraw-Hill, Cambridge, Mass., 1990.
[36] G. F. Cooper, "The computational complexity of probabilistic inference using Bayesian belief networks,"Artificial Intell., vol. 42, nos. 2-3, pp. 393-405, 1990.
[37] S. Sarkar and K. L. Boyer, "Optimal infinite impulse response zero crossing based edge detectors,"Comput. Vision, Graphics and Image Processing Image Understanding, vol. 54, pp. 224-243, Sept. 1991.

Index Terms:
top-down visual processes; image recognition; spatial inference; computer vision; Bayesian networks; perceptual organization; bottom-up visual processes; knowledge base; perceptual inference network; Bayes methods; computer vision; image recognition; knowledge based systems; probability; spatial reasoning
S. Sarkar, K.L. Boyer, "Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 3, pp. 256-274, March 1993, doi:10.1109/34.204907
Usage of this product signifies your acceptance of the Terms of Use.