ML Anthology

Stochastic Image Segmentation by Typical Cuts

Yoram Gdalyahu, Daphna Weinshall, Michael Werman
CVPR 1999 pp. 2596-2601
doi:10.1109/CVPR.1999.784979 /cvpr/1999/gdalyahu1999cvpr-stochastic/

Abstract

We present a stochastic clustering algorithm which uses pairwise similarity of elements, based on a new graph theoretical algorithm for the sampling of cuts in graphs. The stochastic nature of our method makes it robust against noise, including accidental edges and small spurious clusters. We demonstrate the robustness and superiority of our method for image segmentation on a few synthetic examples where other recently proposed methods (such as normalized-cut) fail. In addition, the complexity of our method is lower. We describe experiments with real images showing good segmentation results.

CVPR Semantic Scholar

Cite

Text

Gdalyahu et al. "Stochastic Image Segmentation by Typical Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784979

Markdown

[Gdalyahu et al. "Stochastic Image Segmentation by Typical Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/gdalyahu1999cvpr-stochastic/) doi:10.1109/CVPR.1999.784979

BibTeX

@inproceedings{gdalyahu1999cvpr-stochastic,
  title     = {{Stochastic Image Segmentation by Typical Cuts}},
  author    = {Gdalyahu, Yoram and Weinshall, Daphna and Werman, Michael},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {2596-2601},
  doi       = {10.1109/CVPR.1999.784979},
  url       = {https://mlanthology.org/cvpr/1999/gdalyahu1999cvpr-stochastic/}
}