Non-Parametric Probabilistic Image Segmentation

Marco Andreetto, Lihi Zelnik-Manor, Pietro Perona

ICCV 2007 pp. 1-8

doi:10.1109/ICCV.2007.4408968 /iccv/2007/andreetto2007iccv-non/

Abstract

We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a mixture of Gaussians) the proposed model is principled, provides both hard and probabilistic cluster assignments, as well as the ability to naturally incorporate prior knowledge. While previous probabilistic approaches are restricted to parametric models of clusters (e.g., Gaussians) we eliminate this limitation. The suggested approach does not make heavy assumptions on the shape of the clusters and can thus handle complex structures. Our experiments show that the suggested approach outperforms previous work on a variety of image segmentation tasks.

PDF ICCV Semantic Scholar

Cite

Text

Andreetto et al. "Non-Parametric Probabilistic Image Segmentation." IEEE/CVF International Conference on Computer Vision, 2007. doi:10.1109/ICCV.2007.4408968

Markdown

[Andreetto et al. "Non-Parametric Probabilistic Image Segmentation." IEEE/CVF International Conference on Computer Vision, 2007.](https://mlanthology.org/iccv/2007/andreetto2007iccv-non/) doi:10.1109/ICCV.2007.4408968

BibTeX

@inproceedings{andreetto2007iccv-non,
  title     = {{Non-Parametric Probabilistic Image Segmentation}},
  author    = {Andreetto, Marco and Zelnik-Manor, Lihi and Perona, Pietro},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2007},
  pages     = {1-8},
  doi       = {10.1109/ICCV.2007.4408968},
  url       = {https://mlanthology.org/iccv/2007/andreetto2007iccv-non/}
}