A pixel-parallel anisotropic diffusion algorithm for subjective contour generation

Subjective contours are imaginary contours that the vision system in the human brain generates to complete missing image information. In order to generate subjective contours, the paper proposes an anisotropic diffusion algorithm which can achieve pixel-parallel operation based on the framework of cellular neural networks and cellular automata, which are suitable for LSI realization.

[1]  G. Kanizsa.  Subjective contours. , 1976, Scientific American.

[2]  Michael J. Hawken,et al.  Macaque VI neurons can signal ‘illusory’ contours , 1993, Nature.

[3]  R. von der Heydt,et al.  Mechanisms of contour perception in monkey visual cortex. I. Lines of pattern discontinuity , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[4]  Noboru Ohnishi,et al.  Extracting physically nonexistent contours , 1991, Systems and Computers in Japan.

[5]  T. Morie,et al.  A pixel-parallel image processor for Gabor filtering based on merged analog/digital architecture , 2004, 2004 Symposium on VLSI Circuits. Digest of Technical Papers (IEEE Cat. No.04CH37525).

[6]  R. von der Heydt,et al.  Mechanisms of contour perception in monkey visual cortex. II. Contours bridging gaps , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[7]  Atsushi Iwata,et al.  Gabor-Type Filtering using Transient States of Cellular Neural Networks , 2004, Intell. Autom. Soft Comput..