Assignment of Figural Side to Contours Based on Symmetry, Parallelism, and Convexity

  • Masayuki Kikuchi
  • Kunihiko Fukushima
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2774)

Abstract

We propose a neural network model for the figure-ground organization based on spatial arrangement of contours such as parallelism, symmetry, and on contour convexity. All of them have been manifested as effective factors for figure-ground organization by psychological studies. In order to measure parallelism and symmetry, spatially separated distant contours have to be corresponded. Our model process them by local detectors embedded in hierarchical architecture of network in which image data is pyramidally encoded. We tested our model by computer simulation and succeeded to mimic some human perceptions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Driver, J., Baylis, G.C.: Edge-assignment and figure-ground segmentation in short-term visual matching. Cognitive Psychology 31, 248–306 (1996)CrossRefGoogle Scholar
  2. 2.
    Grossberg, S., Mingolla, E.: Neural dynamics of perceptual grouping: Texture, boundaries, and emergent segmentations. Perception & Psychophysics 38(2), 141–171 (1985)CrossRefGoogle Scholar
  3. 3.
    Kanizsa, G., Gerbino, W.: Convexity and symmetry in figure-ground organization. In: Henle, M. (ed.) Vision and Artifact, pp. 25–32. Springer, New York (1976)Google Scholar
  4. 4.
    Kapadia, M.K., Ito, M., Gilbert, C.D., Westheimer, G.: Improvement in visual sensitivity by changes in local context: parallel studies in human observers and in V1 of alert monkeys. Neuron 15, 843–856 (1995)CrossRefGoogle Scholar
  5. 5.
    Kikuchi, M., Akashi, Y.: A model of border-ownership coding in early vision. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 1069–1074. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Kikuchi, M., Fukushima, K.: Neural network model of the visual system: binding form and motion. Neural Networks 9, 1417–1427 (1996)MATHCrossRefGoogle Scholar
  7. 7.
    Koffka, K.: Principles of Gestalt psychology. Routledge & Kegan Paul Ltd., London (1935)Google Scholar
  8. 8.
    Metzger, W.: Gesetze des Sehens. Verlag von Waldemar Kramer, Frankfurt am Main (1953)Google Scholar
  9. 9.
    Nakayama, K., He, Z.J., Shimojyo, S.: Visual surface representation: a critical link between low-level and higher level vision. In: Kosslyn, S.M., Osherson, D.N. (eds.) Visual Cognition, pp. 1–70. MIT Press, Cambridge (1995)Google Scholar
  10. 10.
    Fukushima, K.: Neocognitron: a hierarchical neural network model capable of visual pattern recognition. Neural Networks 1(2), 119–130 (1988)CrossRefGoogle Scholar
  11. 11.
    Paupathy, A., Conner, E.: Responses to contour features in macaque area V4. Journal of Neurophysiology 82, 2490–2502 (1999)Google Scholar
  12. 12.
    Rubin, E.: Visuall wahrgenommene figuren. Copenhagen (1921)Google Scholar
  13. 13.
    Sajda, P., Finkel, L.H.: Intermediate-level visual representations and the construction of surface perception. Journal of Cognitive Neuroscience 7, 267–291 (1995)CrossRefGoogle Scholar
  14. 14.
    Zhou, H., Friedman, H.S., von der Heydt, R.: Coding of border ownership in monkey visual cortex. The Journal of Neuroscience 20, 6594–6611 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Masayuki Kikuchi
    • 1
  • Kunihiko Fukushima
    • 2
  1. 1.School of Computer ScienceTokyo University of TechnologyTokyoJapan
  2. 2.School of Media ScienceTokyo University of TechnologyTokyoJapan

Personalised recommendations