ML Anthology

Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space

Mikaël Rousson, Thomas Brox, Rachid Deriche
CVPR 2003 pp. 699-706
doi:10.1109/CVPR.2003.1211535 /cvpr/2003/rousson2003cvpr-active/

Abstract

We propose a novel and efficient approach for active unsupervised texture segmentation. First, we show how we can extract a small set of good features for texture segmentation based on the structure tensor and nonlinear diffusion. Then, we propose a variational framework that incorporates these features in a level set based unsupervised segmentation process that adaptively takes into account their estimated statistical information inside and outside the region to segment. The approach has been tested on various textured images, and its performance is favorably compared to recent studies.

PDF CVPR Semantic Scholar

Cite

Text

Rousson et al. "Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211535

Markdown

[Rousson et al. "Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/rousson2003cvpr-active/) doi:10.1109/CVPR.2003.1211535

BibTeX

@inproceedings{rousson2003cvpr-active,
  title     = {{Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space}},
  author    = {Rousson, Mikaël and Brox, Thomas and Deriche, Rachid},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {699-706},
  doi       = {10.1109/CVPR.2003.1211535},
  url       = {https://mlanthology.org/cvpr/2003/rousson2003cvpr-active/}
}