A Biologically-Inspired Theory for Non-axiomatic Parametric Curve Completion

  • Guy Ben-Yosef
  • Ohad Ben-Shahar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6493)


Visual curve completion is typically handled in an axiomatic fashion where the shape of the sought-after completed curve follows formal descriptions of desired, image-based perceptual properties (e.g, minimum curvature, roundedness, etc...). Unfortunately, however, these desired properties are still a matter of debate in the perceptual literature. Instead of the image plane, here we study the problem in the mathematical space \({\mathbf R}^{2}\times {\mathcal S}^{1}\) that abstracts the cortical areas where curve completion occurs. In this space one can apply basic principles from which perceptual properties in the image plane are derived rather than imposed. In particular, we show how a “least action” principle in \({\mathbf R}^{2}\times {\mathcal S}^{1}\) entails many perceptual properties which have support in the perceptual curve completion literature. We formalize this principle in a variational framework for general parametric curves, we derive its differential properties, we present numerical solutions, and we show results on a variety of images.


Tangent Bundle Primary Visual Cortex Illusory Contour Perceptual Property Amodal Completion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ben-Shahar, O., Zucker, S.: The perceptual organization of texture flows: A contextual inference approach. IEEE Trans. Pattern Anal. Mach. Intell. 25, 401–417 (2003)CrossRefGoogle Scholar
  2. 2.
    Ben-Shahar, O.: The Perceptual Organization of Visual Flows. PhD thesis, Yale university (2003)Google Scholar
  3. 3.
    Ben-Yosef, G., Ben-Shahar, O.: Minimum length in the tangent bundle as a model for curve completion. In: Proc. CVPR, pp. 2384–2391 (2010)Google Scholar
  4. 4.
    Citti, G., Sarti, A.: A cortical based model of perceptual completion in the roto-translation space. J. of Math. Imaging and Vision 24, 307–326 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Geisler, W., Perry, J.: Contour statistics in natural images: Grouping across occlusions. Visual Neurosci. 26, 109–121 (2009)CrossRefGoogle Scholar
  6. 6.
    Gerbino, W., Fantoni, C.: Visual interpolation in not scale invariant. Vision Res. 46, 3142–3159 (2006)CrossRefGoogle Scholar
  7. 7.
    Grosof, D., Shapley, R., Hawken, M.: Macaque v1 neurons can signal ’illusory’ contours. Nature 365, 550–552 (1993)CrossRefGoogle Scholar
  8. 8.
    Guttman, S., Kellman, P.: Contour interpolation reveald by a dot localization paradigm. Vision Res. 44, 1799–1815 (2004)CrossRefGoogle Scholar
  9. 9.
    Horn, B.: The curve of least energy. ACM Trans. Math. Software 9, 441–460 (1983)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Hubel, D., Wiesel, T.: Functional architecture of macaque monkey visual cortex. Proc. R. Soc. London Ser. B 198, 1–59 (1977)CrossRefGoogle Scholar
  11. 11.
    Kanizsa, G.: Organization in Vision: Essays on Gestalt Perception. Praeger Publishers, Westport CT (1979)Google Scholar
  12. 12.
    Kellman, P., Shipley, T.: A theory of visual interpolation in object perception. Cognitive Psychology 23, 141–221 (1991)CrossRefGoogle Scholar
  13. 13.
    Kimia, B., Frankel, I., Popescu, A.: Euler spiral for shape completion. Int. J. Comput. Vision 54, 159–182 (2003)CrossRefzbMATHGoogle Scholar
  14. 14.
    Levien, R.: The elastica: a mathematical history. Technical Report UCB/EECS-2008-103, EECS Department, University of California, Berkeley (2008)Google Scholar
  15. 15.
    Mumford, D.: Elastica in computer vision. In: Chandrajit, B. (ed.) Algebric Geometry and it’s Applications. Springer, Heidelberg (1994)Google Scholar
  16. 16.
    O’Neill, B.: Semi-Riemannian Geometry with applications to relativity. Academic Press, London (1983)zbMATHGoogle Scholar
  17. 17.
    Palmer, S.: Vision Science: Photons to Phenomenology. The MIT Press, Cambridge (1999)Google Scholar
  18. 18.
    Petitot, J.: Neurogeometry of v1 and kanizsa contours. AXIOMATHES 13 (2003)Google Scholar
  19. 19.
    Sharon, E., Brandt, A., Basri, R.: Completion energies and scale. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1117–1131 (2000)CrossRefGoogle Scholar
  20. 20.
    Singh, M., Hoffman, D.: Completing visual contours: The relationship between relatability and minimizing inflections. Percept. Psychophys. 61, 943–951 (1999)CrossRefGoogle Scholar
  21. 21.
    Singh, M., Fulvio, J.: Visual extrapolation of contour geometry. Proc. Natl. Acad. Sci. USA 102, 939–944 (2005)CrossRefGoogle Scholar
  22. 22.
    Ullman, S.: Filling in the gaps: The shape of subjective contours and a model for their creation. Biol. Cybern. 25, 1–6 (1976)Google Scholar
  23. 23.
    Von der Heydt, R., Peterhans, E., Baumgartner, G.: Illusory contours and cortical neuron responses. Science 224, 1260–1262 (1984)CrossRefGoogle Scholar
  24. 24.
    Williams, L., Jacobs, D.: Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Comp. 9, 837–858 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Guy Ben-Yosef
    • 1
  • Ohad Ben-Shahar
    • 1
  1. 1.Computer Science DepartmentBen-Gurion UniversityBeer-ShevaIsrael

Personalised recommendations