Model-Based Multi-Object Segmentation via Distribution Matching

Freedman, Daniel; Radke, Richard J.; Zhang, Tao; Jeong, Yongwon; Chen, George T. Y.

doi:10.1109/CVPR.2004.397

Model-Based Multi-Object Segmentation via Distribution Matching

Daniel Freedman, Richard J. Radke, Tao Zhang, Yongwon Jeong, George T. Y. Chen

CVPRW 2004 pp. 11

doi:10.1109/CVPR.2004.397 /cvprw/2004/freedman2004cvprw-modelbased/

Abstract

A new algorithm for the segmentation of 3D deformable objects from 3D images is presented. This algorithm relies on learned shape and appearance models for the objects of interest. The main innovation over similar approaches is that there is no need to compute a pixelwise correspondence between the model and the image; instead, probability distributions are compared. This allows for a faster, more principled algorithm. Results of the algorithm are shown both on synthetic images and for the segmentation of the prostate, bladder, and rectum from medical images.

PDF CVPRW Semantic Scholar

Cite

Text

Freedman et al. "Model-Based Multi-Object Segmentation via Distribution Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004. doi:10.1109/CVPR.2004.397

Markdown

[Freedman et al. "Model-Based Multi-Object Segmentation via Distribution Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004.](https://mlanthology.org/cvprw/2004/freedman2004cvprw-modelbased/) doi:10.1109/CVPR.2004.397

BibTeX

@inproceedings{freedman2004cvprw-modelbased,
  title     = {{Model-Based Multi-Object Segmentation via Distribution Matching}},
  author    = {Freedman, Daniel and Radke, Richard J. and Zhang, Tao and Jeong, Yongwon and Chen, George T. Y.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2004},
  pages     = {11},
  doi       = {10.1109/CVPR.2004.397},
  url       = {https://mlanthology.org/cvprw/2004/freedman2004cvprw-modelbased/}
}