Abstract
The subjective contour generation in the human brain depends on the interaction of local and comprehensive processes realize this mechanism. The purpose of this paper is to propose a model that outputs subjective contours from line figures. This model, for a local process, detects endpoints and generates potential fields that represent probability of an occluding contour’s existence. Each field is anisotropic and spreads perpendicularly to the line figure. Then, for a comprehensive process, the directions of potential fields are corrected to the degree their intersections are maximized in the image. Finally, it fixes subjective contours by tracking potential ridgelines and outputs a result image. The generated subjective contour is smoothly curved and the shape is appropriate compare to what we perceive.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kanizsa, G.: Subjective Contours. Scientific American 234(4), 48–52 (1976)
Kanizsa, G.: Organization in Vision: Essays on Gestalt Perception. Praeger, New York (1979)
von der Heydt, R., Peterhans, E.: Mechanisms of Contour Perception in Monkey Visual Cortex. Jounal of Neuroscience 9, 1731–1748 (1989)
Coren, S.: Subjective Contour and Apparent Depth. Psychological Review 79, 359–367 (1972)
Rock, I., Anson, R.: Illusory Contours as the Solution to a Problem. Perception 8, 665–681 (1979)
Ullman, S.: Filling-in the Gaps: The Shape of Subjective Contours and a Model for Their Generation. Biological Cybernetics 25, 1–6 (1976)
Kass, M., Witkin, A., Terzopouls, D.: Snakes: Active Coutour Models. International Journal of Computer Vision 1, 321–331 (1987)
Zhu, W., Chan, T.: Illusory contours using shape information. UCLA CAM Report, 3–9 (2003)
Williams, L.R., Jacobs, D.W.: Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience. In: International conference on computer vision, pp. 408–415 (1995)
Kim, Y., Morie, T.: Subjective contour generation using a pixel-parallel anisotropic diffusion algorithm. In: International congress series, vol. 1291, pp. 237–240 (2006)
Rodriguez-Sanchez, R., Garcia, J.A., Fdez-Valdivia, J., Fdez-Vidal, X.R.: Origins of illusory percepts in digital images. Pattern Recognition, 33, 2007–2017 (2000)
Ginsburg, A.P.: Is Illusory Triangle Physical or Imaginary? Nature 257, 215–220 (1975)
Skrzypek, J., Ringer, B.: Neural Network Models for Illusory Contour Perception. Conputer Vision and Pattern Recognition, 681–683 (1992)
Shipley, T.F., Kellman, P.J.: Strength of visual interpolation depends on the ratio of physically specified to total edge length. Perception & Psychophysics 52(1), 97–106 (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hirose, O., Nagao, T. (2007). Anisotropic Potential Field Maximization Model for Subjective Contour from Line Figure. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4841. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76858-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-76858-6_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76857-9
Online ISBN: 978-3-540-76858-6
eBook Packages: Computer ScienceComputer Science (R0)