Anisotropic edge detection using mean field annealing
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
An edge detection technique that optimizes edge localization while providing edge continuity and edge thinning is introduced. The solution is obtained by annealing a mean field neural network, providing inexpensive solutions with high parameter insensitivity. Anisotropic diffusion is used to provide localized edge data through the scale-space. Analysis of network parameters, diffusion parameters, network convergence, and scale-space equivalence is provided. Results are shown for real image data and compared with the results of other important edge detection schemes.Keywords
This publication has 5 references indexed in Scilit:
- Adaptive smoothing: a general tool for early visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Scale-space and edge detection using anisotropic diffusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- A NEW METHOD FOR MAPPING OPTIMIZATION PROBLEMS ONTO NEURAL NETWORKSInternational Journal of Neural Systems, 1989
- A Computational Approach to Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Theory of edge detectionProceedings of the Royal Society of London. B. Biological Sciences, 1980