This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
The Perceptual Organization of Texture Flow: A Contextual Inference Approach
April 2003 (vol. 25 no. 4)
pp. 401-417

Abstract—Locally parallel dense patterns—sometimes called texture flows—define a perceptually coherent structure of particular significance to perceptual organization. We argue that with applications ranging from image segmentation and edge classification to shading analysis and shape interpretation, texture flows deserve attention equal to edge segment grouping and curve completion. This paper develops the notion of texture flow from a geometrical point of view to argue that local measurements of such structures must incorporate two curvatures. We show how basic theoretical considerations lead to a unique model for the local behavior of the flow and to a notion of texture flow “good continuation.” This, in turn, translates to a specification of consistency constraints between nearby flow measurements which we use for the computation of globally (piecewise) coherent structure through the contextual framework of relaxation labeling. We demonstrate the results on synthetic and natural images.

[1] S. Axler, P. Bourdon, and W. Ramey, Harmonic Function Theory. Springer-Verlag, 1992.
[2] O. Ben-Shahar and S.W. Zucker, “Beyond Orientation Diffusion: A Curvature-Based Approach to the Analysis of Oriented Patterns,” (In preparation).
[3] M. Black, G. Sapiro, D. Marimont, and D. Heeger, “Robust Anisotropic Diffusion,” IEEE Trans. Image Processing, vol. 7, no. 3, pp. 421-432, 1998.
[4] P. Blomgren and T.F. Chan, “Color TV: Total Variation Methods for Restoration of Vector-Valued Images,” IEEE Trans. Image Processing, vol. 7, no. 3, pp. 304-309, 1998.
[5] P. Breton and S.W. Zucker, “Shadows and Shading Flow Fields,” Proc. Conf. Computer Vision and Pattern Recognition, 1996.
[6] P. Brodatz, Textures: A Photographic Album for Artists and Designers. Dover Publications, 1966.
[7] T. Chan and J. Shen, “Variational Restoration of Non-Flat Image Features: Models and Algorithms,” CAM-TR 99-20, Univ. of California, Los Angeles, 1999.
[8] M. Do Carmo, Differential Geometry of Curves and Surfaces. Prentice-Hall, 1976.
[9] A.R. Forsyth, Lectures on the Differential Geometry of Curves and Surfaces. Cambridge: Univ. Press, 1912.
[10] L. Glass, “Moire Effect from Random Dots,” Nature, vol. 233, no. 5206, pp. 578-580, 1969.
[11] G.H. Granlund and H. Knuttson, Signal Processing for Computer Vision. Kluwer, 1995.
[12] W.C. Graustein, “Harmonic Minimal Surfaces,” Trans. Am. Math. Soc., vol. 47, pp. 173-206, 1940.
[13] G. Hamel, “Zum Gedachtnis an Hermann Amandus Schwarz,” Jahresber, D.M.V., vol. 32, pp. 6-13, 1923.
[14] J.J. Hopfield and D.W. Tank, “Neural Computation of Decisions in Optimization Problems,” Biological Cybernetics, vol. 52, pp. 141-152, 1985.
[15] C.P. Hornung, Background Patterns, Textures, and Tints. Dover Publications, 1976.
[16] D. Hubel and T. Wiesel, “Functional Architecture of Macaque Monkey Visual Cortex,” Proc. Royal Soc. London Series B, vol. 198, pp. 1-59, 1977.
[17] P.S. Huggins and S.W. Zucker, “How Folds Cut a Scene,” Proc. Fourth Int'l Workshop Visual Form, 2001.
[18] R.A. Hummel and S.W. Zucker, “On the Foundations of the Relaxation Labeling Proceeses,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 5, pp. 267-287, 1983.
[19] L.A. Iverson and S.W. Zucker, “Logical/Linear Operators for Image Curves,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 10, pp. 982-996, Oct. 1995.
[20] G. Kanizsa, Organization in Vision: Essays on Gestalt Perception. Praeger, 1979.
[21] M. Kass and A. Witkin, “Analyzing Oriented Patterns,” Computer Vision, Graphics, and Image Processing, vol. 37, pp. 362-385, 1987.
[22] D.R.T. Keeble, F.A.A. Kingdom, and M.J. Morgan, “The Orientational Resolution of Human Texture Perception,” Vision Research, vol. 37, no. 21, pp. 2993-3007, 1997.
[23] B.K. Kimia, L. Frankel, and A.M. Popescu, “Euler Spiral for Shape Completion,” Proc. IEEE CS Workshop Perceptual Organization in Computer Vision, 1999.
[24] R. Kimmel and N. Sochen, “Orientation Diffusion or How to Comb a Porcupine?” CIS 2000-02, Technion-Israel Inst. of Tech nology, 2000.
[25] J. Kittler and J. Illingworth, "Relaxation Labeling Algorithms—A Review," Image and Vision Computers, vol. 3, no. 4, pp. 206-216, 1985.
[26] J.J. Koenderink, “The Structure of Images,” Biological Cybernetics, vol. 50, pp. 363-370, 1984.
[27] J.J. Koenderink and A.J. van Doorn, “Local Structure of Movement Parallax of the Plane,” J. Optical Soc. Am. , vol. 66, no. 7, pp. 717-723, 1976.
[28] M.S. Landy and J.R. Bergen, “Texture Segregation and Orientation Gradient,” Vision Research, vol. 31, no. 4, pp. 679-691, 1991.
[29] T.S. Lee, “A Bayesian Framework for Understanding Texture Segmentation in the Primary Visual Cortex,” Vision Research, vol. 35, no. 18, pp. 2643-2657, 1993.
[30] D.G. Lowe, Perceptual Organization and Visual Recognition. Boston: Kluwer Academic, 1985.
[31] D. Marr, Vision. W.H. Freeman and Company, 1982.
[32] D.A. Miller and S.W. Zucker, “Computing with Self-Excitatory Cliques: A Model and Application to Hyperacuity-Sclae Computation in Visual Cortex,” Neural Computation, vol. 11, pp. 21-66, 1999.
[33] J.L. Mohammed, R.A. Hummel, and S.W. Zucker, “A Gradient Projection Algorithm for Relaxation Methods,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 5, no. 3, pp. 330-332, 1983.
[34] J.D. Murray, Mathematical Biology. Springer-Verlag, 1989.
[35] J.C.C. Nitsche, Lectures on Minimal Surfaces. Cambridge Univ. Press, 1989.
[36] H.C. Nothdurft, “Sensitivity for Structure Gradient in Texture Discrimination Tasks,” Vision Research, vol. 25, no. 12, pp. 1957-1968, 1985.
[37] H.C. Nothdurft, “Texture Segmentation and Pop-Out from Orientation Contrast,” Vision Research, vol. 31, no. 6, pp. 1073-1078, 1991.
[38] B. O'Neill, Elementary Differential Geometry. Academic Press, 1966.
[39] P. Parent and S.W. Zucker, “Trace Inference, Curvature Consistency and Curve Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 8, pp. 823-839, 1989.
[40] P. Perona, “Orientation Diffusion,” IEEE Trans. Image Processing, vol. 7, no. 3, pp. 457-467, 1998.
[41] P. Perona and J. Malik, "Scale-Space and Edge Detection Using Anisotropic Diffusion," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 629639, July 1990.
[42] A.A. Rao and R.C. Jain, “Computerized Flow Field Analysis: Oriented Texture Fields,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 693-709, July 1992.
[43] A.R. Rao and B.G. Schunck, “Computing Oriented Texture Fields,” Proc. CVGIP: Graphical Models and Image Processing, vol. 53, no. 2, pp. 157-185, 1991.
[44] D. Regan, L.V. Hajdur, and X.H. Hong, “Two-Dimensional Aspect Ratio Indiscrimination for Shape Defined by Orientation Texture,” Vision Research, vol. 36, no. 22, pp. 3695-3702, 1996.
[45] G. Sapiro and D. Ringach, “Anisotropic Diffusion of Multivalued Images with Applications to Color Filtering,” IEEE Trans. Image Processing, vol. 5, pp. 1582-1586, 1996.
[46] J. Shi and J. Malik, “Normalized Cuts and Image Segmenation,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 731-737, June 1997.
[47] M. Sigman, G.A. Cecchi, C.D. Gilbert, and M.O. Magnasco, “On a Common Circle: Natural Scenes and Gestalt Rules,” Proc. Nat'l Academy Science USA, vol. 98, no. 4, pp. 1935-1940, Feb. 2001.
[48] N. Sochen, R. Kimmel, and A.M. Bruckstein, “Diffusion and Confusions in Signal and Image Processing,” J. Math. Imaging and Vision, 2001. To appear.
[49] N. Sochen, R. Kimmel, and R. Malladi, “A Geometrical Framework for Low Level Vision,” IEEE Trans. Image Processing, vol. 7, no. 3, pp. 310-318, 1998.
[50] K.A. Stevens, “Computation of Locally Parallel Structure,” Biological Cybernetics, vol. 29, pp. 19-28, 1978.
[51] K.A. Stevens, “The Line of Curvature Constraint and the Interpretation of 3D Shape from Parallel Surface Contours,” Proc. Int'l Joint Conf. Artificial Intelligence, pp. 1057-1061, 1983.
[52] B. Tang, G. Sapiro, and V. Caselles, “Diffusion of General Data on Non-Flat Manifolds via Harmonic Maps Theory: The Direction Diffusion Case,” Int'l J. Computer Vision, to appear.
[53] J.T. Todd and F. D. Reichel, “Visual Perception of Smoothly Curved Surfaces from Double-Projected Contour Patterns,” J. Experimental Psychology: Human Perception and Performance, vol. 16, no. 3, pp. 665-674, 1990.
[54] P.W. Verbeek, L.J. van Vliet, and J. van de Weijer, “Improved Curvature and Anisotropy Estimation for Curved Line Bundles,” Proc. Int'l Conf. Pattern Recognition, pp. 528-533, 1998.
[55] D.L. Waltz, “Understanding Line Drawings of Scenes with Shadows,” The Psychology of Computer Vision, P.H. Winston, ed. pp. 19-91, New York: McGraw-Hill, 1975.
[56] T. Watanabe and P. Cavanagh, “Texture Laciness: The Texture Equivalent of Transparancy?” Perception, vol. 25, pp. 293-303, 1996.
[57] J. Weickert, “A Review of Nonlinear Diffusion Filtering,” Scale-Space Theory in Computer Vision, B. ter Haar Romeny, L. Florack, J.J. Koenderink, and M. Viergever, eds., vol. 1252, pp. 3-28, 1997.
[58] M. Wertheimer, “Gestalt Theory,” A Source Book of Gestalt Psychology, W.D. Ellis, ed., pp. 1-11, Routledge&Kegan Paul Ltd., 1955.
[59] M. Wertheimer, “Laws of Organization in Perceptual Forms,” A Source Book of Gestalt Psychology, W.D. Ellis, ed., pp. 71-88, Routledge&Kegan Paul Ltd., 1955.
[60] 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.
[61] A.P. Witkin, “Scale-Space Filtering,” Proc. Int'l Joint Conf. Artificial Intelligence, pp. 1019-1022, 1983.
[62] A.P. Witkin and J.M. Tenenbaum, “On the Role of Structure in Vision,” Human and Machine Vision, J. Beck, B. Hope, and A. Rosenfeld, eds., pp. 481-542, Academic Press, 1983.
[63] S.W. Zucker, “Computational and Psychophysical Experiments in Grouping: Early Orientation Selection,” Human and Machine Vision, J. Beck, B. Hope, and A. Rosenfeld, eds., pp. 545-567, Academic Press, 1983.

Index Terms:
Texture flow, perceptual organization, social conformity of a line, good continuation, texture segmentation, line discontinuities, point singularities, shading flow, local parallelism, orientation diffusion, tangential curvature, normal curvature, relaxation labeling.
Citation:
Ohad Ben-Shahar, Steven W. Zucker, "The Perceptual Organization of Texture Flow: A Contextual Inference Approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 4, pp. 401-417, April 2003, doi:10.1109/TPAMI.2003.1190568
Usage of this product signifies your acceptance of the Terms of Use.