Figure-Ground Discrimination by Mean Field Annealing

Abstract

We formulate the figure-ground discrimination problem as a combinatorial optimization problem. We suggest a cost function that makes explicit a definition of shape based on interactions between image edges. These interactions have some mathematical analogy with interacting spin systems — a model that is well suited for solving combinatorial optimization problems. We devise a mean field annealing method for finding the global minimum of such a spin system and the method successfully solves for the figure-ground problem.

Cite

Text

Hérault and Horaud. "Figure-Ground Discrimination by Mean Field Annealing." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_7

Markdown

[Hérault and Horaud. "Figure-Ground Discrimination by Mean Field Annealing." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/herault1992eccv-figure/) doi:10.1007/3-540-55426-2_7

BibTeX

@inproceedings{herault1992eccv-figure,
  title     = {{Figure-Ground Discrimination by Mean Field Annealing}},
  author    = {Hérault, Laurent and Horaud, Radu},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {58-66},
  doi       = {10.1007/3-540-55426-2_7},
  url       = {https://mlanthology.org/eccv/1992/herault1992eccv-figure/}
}