Skip to main content
Log in

General Geometric Good Continuation: From Taylor to Laplace via Level Sets

International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

Good continuation is the Gestalt observation that parts often group in particular ways to form coherent wholes. Perceptual integration of edges, for example, involves orientation good continuation, a property which has been exploited computationally very extensively. But more general local-global relationships, such as for shading or color, have been elusive. While Taylor’s Theorem suggests certain modeling and smoothness criteria, the consideration of level set geometry indicates a different approach. Using such first principles we derive, for the first time, a generalization of good continuation to all those visual structures that can be abstracted as scalar functions over the image plane. Based on second order differential constraints that reflect good continuation, our analysis leads to a unique class of harmonic models and a cooperative algorithm for structure inference. Among the different applications of good continuation, here we apply these results to the denoising of shading and intensity distributions and demonstrate how our approach eliminates spurious measurements while preserving both singularities and regular structure, a property that facilitates higher level processes which depend so critically on both of these classes of visual structures.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Alvarez, L., & Mazorra, L. (1994). Signal and image restoration using shock filters and anisotropic diffusion. SIAM Journal on Numerical Analysis, 31(2), 590–605.

    Article  MATH  MathSciNet  Google Scholar 

  • Ben-Shahar, O. (2003). The perceptual organization of visual flows. Ph.D. thesis, Yale university.

  • Ben-Shahar, O. (2006). Visual saliency and texture segregation without feature gradient. Proceedings of the National Academy of Sciences of the USA, 103, 15704–15709.

    Article  Google Scholar 

  • Ben-Shahar, O., & Zucker, S. (2003). The perceptual organization of texture flows: A contextual inference approach. IEEE Transactions Pattern Analysis and Machine Intelligence, 25(4), 401–417.

    Article  Google Scholar 

  • Ben-Shahar, O., & Zucker, S. (2004). Geometrical computations explain projection patterns of long range horizontal connections in visual cortex. Neural Computing, 16(3), 445–476.

    Article  MATH  Google Scholar 

  • Ben-Shahar, O., & Zucker, S. (2004). Hue geometry and horizontal connections. Neural Networks, 17, 753–771.

    Article  Google Scholar 

  • Breton, P., Iverson, L., Langer, M., & Zucker, S. (1992). A new approach to shape from shading. In G. Carpenter & S. Grossberg (Eds.), Neural networks for vision and image processing, Chap. 5 (pp. 111–131). Cambridge: Cambridge MIT Press.

    Google Scholar 

  • Cao, F. (2004). Application of the gestalt principle to the detection of good continuation and corners in image level lines. Comput. Vis. Sci., 7, 3–13.

    Article  MATH  MathSciNet  Google Scholar 

  • Carbal, B., & Leedom, L. (1993). Imaging vector fields using line integral convolution. In Proceedings of SIGGRAPH (pp. 263–270).

  • Caselles, V., Kimmel, R., Sapiro, G., & Sbert, C. (1997a). Minimal surfaces: a three dimensional segmentation approach. Numerische Mathematik, 77(4), 423–451.

    Article  MATH  MathSciNet  Google Scholar 

  • Caselles, V., Kimmel, R., Sapiro, G., & Sbert, C. (1997b). Minimal surfaces based object segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4), 294–298.

    Article  MathSciNet  Google Scholar 

  • Caselles, V., Coll, B., & Morel, J.-M. (2002). Geometry and color in natural images. Journal of Mathematical Imaging and Vision, 16, 89–105.

    Article  MATH  MathSciNet  Google Scholar 

  • De Valois, R., Albrecht, D., & Thorell, L. (1982). Spatial frequency selectivity of cells in macaque visual cortex. Vision Research, 22, 545–559.

    Article  Google Scholar 

  • Dierkes, U., Hildebrandt, S., Küster, A., & Wohrlab, O. (1992). Minimal surfaces. Berlin: Springer.

    Google Scholar 

  • Duncan, J., & Birkholzer, T. (1992). Reinforcement of linear structure using parametrized relaxation labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(5), 502–515.

    Article  Google Scholar 

  • Fischler, M. (1994). The perception of linear structure: a generic linker. In Proceedings of the image understanding workshop (Vol. 2, pp. 1565–1579).

  • Graustein, W. (1940). Harmonic minimal surfaces. Transactions of the American Mathematical Society, 47, 173–206.

    Article  MATH  MathSciNet  Google Scholar 

  • Guy, G., & Medioni, G. (1996). Inferring global perceptual contours from local features. International Journal of Computer Vision, 20(1/2), 113–133.

    Article  Google Scholar 

  • Guy, G., & Medioni, G. (1997). Inference of surfaces, 3d curves, and junctions from sparse, noisy 3d data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(11), 1265–1277.

    Article  Google Scholar 

  • Hamel, G. (1923). Zum Gedachtnis an Hermann Amandus Schwarz. Jahresberichte D.M.V., 32, 6–13.

    MATH  Google Scholar 

  • Hoffman, D. (1998). Visual Intelligence. Norton.

  • Hopfield, J., & Tank, D. (1985). Neural computation of decisions in optimization problems. Biological Cybernetics, 52, 141–152.

    MATH  MathSciNet  Google Scholar 

  • Hubel, D., & Wiesel, T. (1977). Functional architecture of macaque monkey visual cortex. Proceedings of the Royal Society London Series B, 198, 1–59.

    Article  Google Scholar 

  • Hummel, R., & Zucker, S. (1983). On the foundations of the relaxation labeling processes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5, 267–287.

    Article  MATH  Google Scholar 

  • Jain, A. (1989). Fundamentals of digital image processing. Prentice-Hall: Englewood Cliffs.

    MATH  Google Scholar 

  • John, F. (1982). Partial differential equations. New York: Springer.

    Google Scholar 

  • Keil, M., Cristobal, G., & Neumann, H. (2006). Gradient representation and perception in the early visual system—a novel account of Mach band formation. Vision Research, 46, 2659–2674.

    Article  Google Scholar 

  • Kimia, B., Frankel, L., & Popescu, A. (1999). Euler spiral for shape completion. In Proceedings of the IEEE Computer Society workshop on perceptual organization in computer vision.

  • Kimmel, R., Malladi, R., & Sochen, N. (2000). Images as embedded maps and minimal surfaces: Movies, color, texture, and volumetric medical images. International Journal of Computer Vision, 39(2), 111–129.

    Article  MATH  Google Scholar 

  • Kittler, J., & Illingworh, J. (1985). Relaxation labeling algorithms—a review. Image and Vision Computing (pp. 206–216).

  • Koenderink, J., & van Doorn, A. (2002). Image processing done right. In Proceedings of the European conference on computer vision (pp. 158–172).

  • Koffka, K. (1935). Principles of Gestalt Psychology. London: Routledge & Kegan Paul.

    Google Scholar 

  • Malik, J., & Perona, P. (1990). Preattentive texture discrimination with early vision mechanisms. Journal of the Optical Society of America, 7(5), 923–932.

    Article  Google Scholar 

  • Miller, D., & Zucker, S. (1999). Computing with self-excitatory cliques: a model and application to hyperacuity-scale computation in visual cortex. Neural Computing, 11, 21–66.

    Article  Google Scholar 

  • Mumford, D. (1994). Elastica in computer vision. In B. Chandrajit (Ed.), Algebraic geometry and its applications. Berlin: Springer.

    Google Scholar 

  • Nitsche, J. (1989). Lectures on Minimal Surfaces. Cambridge: Cambridge University Press.

    MATH  Google Scholar 

  • O’Neill, B. (1966). Elementary differential geometry. New York: Academic Press.

    MATH  Google Scholar 

  • Parent, P., & Zucker, S. (1989). Trace inference, curvature consistency, and curve detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(8), 823–839.

    Article  Google Scholar 

  • Pearl, J. (1988). Probabilistic reasoning in intelligent systems: networks of plausible inference. San Mateo: Morgan Kaufmann.

    Google Scholar 

  • Pelillo, M. (1997). The dynamics of nonlinear relaxation labeling processes. Journal of Mathematical Imaging and Vision, 7, 309–323.

    Article  MathSciNet  Google Scholar 

  • Perona, P., & Malik, J. (1990). Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7), 629–639.

    Article  Google Scholar 

  • Richards, W., Keonderink, J., & Hoffman, D. (1987). Inferring 3d shapes from 2d silhouettes. Journal of the Optical Society of America, 4, 1168–1175.

    Article  Google Scholar 

  • Šára, R. (1995). Isophotes: the key to tractable local shading analysis. In Proceedings of the international conference on computer analysis of images and patterns (pp. 416–423).

  • Savadjiev, P., Zucker, S., & Siddiqi, K. (2007). On the differential geometry of 3d flow patterns: generalized helicoids and diffusion MRI analysis. In Proceedings of the IEEE international conference on computer vision (pp. 1–8).

  • Sha’ashua, A., & Ullman, S. (1988). Structural saliency: the detection of globally salient structures using a locally connected network. In Proceedings of the IEEE international conference on computer vision (pp. 321–327).

  • Sharon, E., Brandt, A., & Basri, R. (2000). Completion energies and scale. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(10), 1117–1131.

    Article  Google Scholar 

  • Sochen, N., Kimmel, R., & Malladi, R. (1998). A general framework for low level vision. IEEE Transaction on Image Processing, 7(3), 310–318.

    Article  MATH  MathSciNet  Google Scholar 

  • Tang, B., Sapiro, G., & Caselles, V. (2000). Diffusion of general data on non-flat manifolds via harmonic maps theory: the direction diffusion case. International Journal of Computer Vision, 36(2), 149–161.

    Article  Google Scholar 

  • Torsello, A., & Pelillo, M. (2000). Continuous-time relaxation labeling processes. Pattern Recognition, 33, 1897–1908.

    Article  Google Scholar 

  • Ullman, S. (1976). Filling in the gaps: the shape of subjective contours and a model for their creation. Biological Cybernetics, 25, 1–6.

    MathSciNet  Google Scholar 

  • Waltz, D. (1975). Understanding line drawings of scenes with shadows. In P. Winston (Ed.), The psychology of computer vision (pp. 19–91). New York: McGraw-Hill.

    Google Scholar 

  • Wertheimer, M. (1955). Laws of organization in perceptual forms. In W. Ellis (Ed.), A source book of Gestalt Psych. (pp. 71–88). London: Routledge & Kegan Paul.

    Google Scholar 

  • Williams, L., & Jacobs, D. (1997). Stochastic completion fields: a neural model of illusory contour shape and salience. Neural Computing, 9(4), 837–858.

    Article  Google Scholar 

  • Witkin, A., & Tenenbaum, J. (1983). On the role of structure in vision. In J. Beck, B. Hope, & A. Rosenfeld (Eds.), Human and machine vision (pp. 481–542). New York: Academic Press.

    Google Scholar 

  • Zucker, S., Rosenfeld, A., & Davis, L. (1975). General purpose models: expectations about the unexpected. In Proceedings of the international joint conference on artificial intelligence (pp. 716–721).

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ohad Ben-Shahar.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ben-Shahar, O., Zucker, S. General Geometric Good Continuation: From Taylor to Laplace via Level Sets. Int J Comput Vis 86, 48–71 (2010). https://doi.org/10.1007/s11263-009-0255-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-009-0255-8

Keywords

Navigation