Segmentation and Grouping of Object Boundaries Using Energy Minimization

Abstract

An algorithm is described which performs curvilinear grouping of image edge elements for detecting object boundaries. The method works by generating hypotheses and selecting the best one. A neighborhood definition based on Delaunay graph is used to keep the number of generated hypotheses small. An energy minimizing curve is fit to the generated hypotheses to evaluate the grouping and locate discontinuities.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Trytten and Tüceryan. "Segmentation and Grouping of Object Boundaries Using Energy Minimization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139803

Markdown

[Trytten and Tüceryan. "Segmentation and Grouping of Object Boundaries Using Energy Minimization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/trytten1991cvpr-segmentation/) doi:10.1109/CVPR.1991.139803

BibTeX

@inproceedings{trytten1991cvpr-segmentation,
  title     = {{Segmentation and Grouping of Object Boundaries Using Energy Minimization}},
  author    = {Trytten, Deborah Anne and Tüceryan, Mihran},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {730-731},
  doi       = {10.1109/CVPR.1991.139803},
  url       = {https://mlanthology.org/cvpr/1991/trytten1991cvpr-segmentation/}
}