Anisotropic edge detection using mean field annealing

Scott T. Acton, Alan C. BovikICASSP 1992 · OpenReview

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.<
BibTeX
@inproceedings{acton1992anisotropic,
  author = {Scott T. Acton and Alan C. Bovik},
  title = {{Anisotropic edge detection using mean field annealing}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1992},
  url = {https://openreview.net/forum?id=lS6s_vyO0},
}

Loading related content...

Figure