ML Anthology

Globally Optimal Grouping for Symmetric Boundaries

Joachim S. Stahl, Song Wang
CVPR 2006 pp. 1030-1037
doi:10.1109/CVPR.2006.127 /cvpr/2006/stahl2006cvpr-globally/

Abstract

Many natural and man-made structures have a boundary that shows certain level of bilateral symmetry, a property that has been used to solve many computer-vision tasks. In this paper, we present a new grouping method for detecting closed boundaries with symmetry. We first construct a new type of grouping token in the form of a symmetric trapezoid, with which we can flexibly incorporate various boundary and region information into a unified grouping cost function. Particularly, this grouping cost function integrates Gestalt laws of proximity, closure, and continuity, besides the desirable boundary symmetry. We then develop a graph algorithm to find the boundary that minimizes this grouping cost function in a globally optimal fashion. Finally, we test this method by some experiments on a set of natural and medical images.

CVPR Semantic Scholar

Cite

Text

Stahl and Wang. "Globally Optimal Grouping for Symmetric Boundaries." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.127

Markdown

[Stahl and Wang. "Globally Optimal Grouping for Symmetric Boundaries." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/stahl2006cvpr-globally/) doi:10.1109/CVPR.2006.127

BibTeX

@inproceedings{stahl2006cvpr-globally,
  title     = {{Globally Optimal Grouping for Symmetric Boundaries}},
  author    = {Stahl, Joachim S. and Wang, Song},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1030-1037},
  doi       = {10.1109/CVPR.2006.127},
  url       = {https://mlanthology.org/cvpr/2006/stahl2006cvpr-globally/}
}