Multilabel Random Walker Image Segmentation Using Prior Models

Grady, Leo J.

doi:10.1109/CVPR.2005.239

Multilabel Random Walker Image Segmentation Using Prior Models

Leo J. Grady

CVPR 2005 pp. 763-770

doi:10.1109/CVPR.2005.239 /cvpr/2005/grady2005cvpr-multilabel/

Abstract

The recently introduced random walker segmentation algorithm by Grady and Funka-Lea (2004) has been shown to have desirable theoretical properties and to perform well on a wide variety of images in practice. However, this algorithm requires user-specified labels and produces a segmentation where each segment is connected to a labeled pixel. We show that incorporation of a nonparametric probability density model allows for an extended random walkers algorithm that can locate disconnected objects and does not require user-specified labels. Finally, we show that this formulation leads to a deep connection with the popular graph cuts method by Boykov et al. (2001) and Wu and Leahy (1993).

CVPR Semantic Scholar

Cite

Text

Grady. "Multilabel Random Walker Image Segmentation Using Prior Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.239

Markdown

[Grady. "Multilabel Random Walker Image Segmentation Using Prior Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/grady2005cvpr-multilabel/) doi:10.1109/CVPR.2005.239

BibTeX

@inproceedings{grady2005cvpr-multilabel,
  title     = {{Multilabel Random Walker Image Segmentation Using Prior Models}},
  author    = {Grady, Leo J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {763-770},
  doi       = {10.1109/CVPR.2005.239},
  url       = {https://mlanthology.org/cvpr/2005/grady2005cvpr-multilabel/}
}