This Article 
 Bibliographic References 
 Add to: 
Completion Energies and Scale
October 2000 (vol. 22 no. 10)
pp. 1117-1131

Abstract—The detection of smooth curves in images and their completion over gaps are two important problems in perceptual grouping. In this study, we examine the notion of completion energy of curve elements, showing, and exploiting its intrinsic dependence on length and width scales. We introduce a fast method for computing the most likely completion between two elements, by developing novel analytic approximations and a fast numerical procedure for computing the curve of least energy. We then use our newly developed energies to find the most likely completions in images through a generalized summation of induction fields. This is done through multiscale procedures, i.e., separate processing at different scales with some interscale interactions. Such procedures allow the summation of all induction fields to be done in a total of only $O(N \log N)$ operations, where $N$ is the number of pixels in the image. More important, such procedures yield a more realistic dependence of the induction field on the length and width scales: The field of a long element is very different from the sum of the fields of its composing short segments.

[1] T.D. Alter and R. Basri, “Extracting Salient Curves from Images: An Analysis of the Saliency Network,” Int'l J. Computer Vision, vol. 27, no. 1, pp. 51-69, 1998.
[2] M. Brady, W.E.L. Grimson, and D.J. Langridge, “Shape Encoding and Subjective Contours,” Proc. First Ann. Conf. Artifical Intelligence, 1980.
[3] A. Brandt, “Multilevel Computations of Integral Transforms and Particle Interactions with Oscillatory Kernels,” Computer Physics Comm., vol. 65, pp. 24-38, 1991.
[4] A. Brandt and J. Dym, “Fast Calculation of Multiple Line Integrals,” SIAM J. Scientific Computation, vol. 20, no. 4, pp. 1,417-1,429, 1999.
[5] A.M. Bruckstein and A.N. Netravali, “On Minimal Energy Trajectories,” Computer Vision, Graphics, and Image Processing, vol. 49, pp. 283-296, 1990.
[6] J. Dolan and R. Weiss, “Perceptual Grouping of Curved Lines,” Proc. Image Understanding Workshop, pp. 1135-1145, 1989.
[7] L.E. Elsgolts, “Calculus of Variations,” Int'l Series of Monographs on Pure and Applied Math., vol. 19, 1961.
[8] D.J. Field, A. Hayes, and R.F. Hess, “Contour Integration by the Human Visual System: Evidence for a Local“Association Field,” Vision Research, vol. 33, no. 2, pp. 173-193, 1993.
[9] S. Grossberg and E. Mingolla, “The Role of Illusory Contours in Visual Segmentation,” The Perception of Illusory Contours, S. Petry, and G. Meyer, eds., pp. 116-125, New York: Springer-Verlag, 1987.
[10] G. Guy and G. Medioni, “Inferring Global Perceptual Contours from Local Features,” Int'l J. Computer Vision, vol. 20, pp. 113-133, 1996.
[11] R. Heitger and R. Von der Heydt, "A computational model of neural contour processing, figure-ground segregation and illusory contours," Proc. IEEE Int'l Conf. Computer Vision, pp. 32-40, 1993.
[12] 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.
[13] B.K.P. Horn,“The curve of least energy,” ACM Trans. Mathematical Software, vol. 5, no. 4, pp. 442-460, December 1983.
[14] G. Kanizsa, Organization in Vision. New York: Praeger, 1979.
[15] M.K. Kapadia, M. Ito, C.D. Gilbert, and G. Westheimer, “Improvement in Visual Sensitivity by Changes in Local Context: Parallel Studies in Human Observers and in V1 of Alert Monkeys,” Neuron, vol. 15, pp. 843-856, 1995.
[16] P.J. Kellman and T.F. Shipley, “A Theory of Visual Interpolation in Object Perception,” Cognitive Psychology, vol. 23, pp. 141-221, 1991.
[17] D. Mumford, “Elastica and Computer Vision,” Algebraic Geometry and Its Applications, C. Bajaj, ed., pp. 491-506, Springer Verlag, 1994.
[18] M. Nitzberg and D. Mumford,“The 2.1-D sketch,” Proc. 3rd Int’l Conf. on Computer Vision, pp. 138-144, 1990.
[19] Handbook of Applied Mathematics, C.E. Pearson, ed., second ed. New York: Van Nostrand Reinhold Company, 1983.
[20] 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.
[21] U. Polat and D. Sagi, “Lateral Interactions Between Spatial Channels: Suppression and Facilitation Revealed by Lateral Masking Experiments,” Vision Research, vol. 33, no. 7, pp. 993-999, 1993.
[22] N. Rubin, R. Shapley, and K. Nakayama, “Rapid Propagation Speed of Signals Triggering Illusory Contours,” Investigative Opthalmology and Visual Science , vol. 36, p. 1,037, 1995.
[23] W.S. Rutkowski, “Shape Completion,” Computer Graphics and Image Processing, vol. 9, no. 1, pp. 89-101, 1979.
[24] 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.
[25] E. Saund, “Perceptual Organization of Occluding Contours Generated by Opaque Surfaces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 624-630, 1999.
[26] 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.
[27] K.K. Thornber and L.R. Williams, “Analytic Solution of Stochastic Completion Fields,” Biological Cybernetics, vol. 75, pp. 141-151, 1996.
[28] K.K. Thornber and L.R. Williams, “Characterizing the Distribution of Completion Shapes with Corners Using a Mixture of Random Processes,” Int'l Workshop Energy Minimization Methods in Computer Vision and Pattern Recognition, 1996.
[29] S. Ullman, “Filling-In the Gaps: The Shape of Subjective Contours and a Model for Their Generation,” Biological Cybernetics, vol. 25, pp. 1-6, 1976.
[30] I. Weiss,“3D shape representation by contours,” Computer Vision, Graphics and Image Processing, vol. 41, pp. 80-100, 1988.
[31] L.R Williams and A.R. Hanson, “Perceptual Completion of Occluded Surfaces,” Proc. IEEE Computer Vision and Pattern Recognition, 1994.
[32] 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.
[33] A.H. Bratt et al., "Design-For-Test Structure to Facilitate Test Vector Application with Low Performance Loss in Non-Test Mode," Electronics Letters, vol. 29, no. 16, Aug. 1993, pp. 1438-1440.
[34] S. Yen and L. Finkel, “Pop-Out of Salient Contours in a Network Based on Striate Cortical Connectivity,” Investigative Opthalmology and Visual Science (ARVO), vol. 37, no. 3, 1996.
[35] S.W. Zucker and R.A. Hummel, “Toward a Low-Level Description of Dot Clusters: Labeling Edge, Interior, and Noise Points,” Computer Graphics and Image Processing, vol. 9, no. 3, pp. 213-234, 1979.
[36] S.W. Zucker, C. David, A. Dobbins, and L. Iverson, "The Organization of Curve Detection: Coarse Tangent Fields and Thin Spline Coverings," Proc. Second Int'l Conf. Computer Vision, pp. 568-577,Tampa, Fla., Dec. 1988.

Index Terms:
Curve completion, curve saliency, least-energy curve, perceptual grouping, elastica curve, scale, induction field, completion field, fast summation, multiscale.
Eitan Sharon, Achi Brandt, Ronen Basri, "Completion Energies and Scale," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1117-1131, Oct. 2000, doi:10.1109/34.879792
Usage of this product signifies your acceptance of the Terms of Use.