Assignment of Figural Side to Contours Based on Symmetry, Parallelism, and Convexity
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.
Unable to display preview. Download preview PDF.
- 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
- 7.Koffka, K.: Principles of Gestalt psychology. Routledge & Kegan Paul Ltd., London (1935)Google Scholar
- 8.Metzger, W.: Gesetze des Sehens. Verlag von Waldemar Kramer, Frankfurt am Main (1953)Google Scholar
- 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
- 11.Paupathy, A., Conner, E.: Responses to contour features in macaque area V4. Journal of Neurophysiology 82, 2490–2502 (1999)Google Scholar
- 12.Rubin, E.: Visuall wahrgenommene figuren. Copenhagen (1921)Google Scholar
- 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