ML Anthology

Region Segmentation via Deformable Model-Guided Split and Merge

Lifeng Liu, Stan Sclaroff
ICCV 2001 pp. 98-104
doi:10.1109/ICCV.2001.10048 /iccv/2001/liu2001iccv-region/

Abstract

An improved method for deformable shape-based image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. Perceptually-motivated criteria are used to determine where/how to split regions, based on the local shape properties of the region group's bounding contour. A globally consistent interpretation is determined in part by the minimum description length principle. Experiments show that model-guided split and merge yields a significant improvement in segmention over a method that uses merging alone.

ICCV Semantic Scholar

Cite

Text

Liu and Sclaroff. "Region Segmentation via Deformable Model-Guided Split and Merge." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10048

Markdown

[Liu and Sclaroff. "Region Segmentation via Deformable Model-Guided Split and Merge." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/liu2001iccv-region/) doi:10.1109/ICCV.2001.10048

BibTeX

@inproceedings{liu2001iccv-region,
  title     = {{Region Segmentation via Deformable Model-Guided Split and Merge}},
  author    = {Liu, Lifeng and Sclaroff, Stan},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {98-104},
  doi       = {10.1109/ICCV.2001.10048},
  url       = {https://mlanthology.org/iccv/2001/liu2001iccv-region/}
}