mAP Representations and Coding-Based Priors for Segmentation

Keeler, Kenneth

doi:10.1109/CVPR.1991.139727

mAP Representations and Coding-Based Priors for Segmentation

Kenneth Keeler

CVPR 1991 pp. 420-425

doi:10.1109/CVPR.1991.139727 /cvpr/1991/keeler1991cvpr-map/

Abstract

The Bayesian segmentation model developed is motivated by consideration of the information needed for higher-level visual processing. A segmentation is regarded as a collection of parameters defining an image-valued stochastic process by separating topological (adjacency) and metric (shape) properties of the subdivision and intensity properties of each region. The prior selection is structured accordingly. The novel part of the representation, the subdivision topology, is assigned a prior by universal coding arguments, using the minimum description-length philosophy that the best segmentation allows the most efficient representation of visual data.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

CVPR Semantic Scholar

Cite

Text

Keeler. "mAP Representations and Coding-Based Priors for Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139727

Markdown

[Keeler. "mAP Representations and Coding-Based Priors for Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/keeler1991cvpr-map/) doi:10.1109/CVPR.1991.139727

BibTeX

@inproceedings{keeler1991cvpr-map,
  title     = {{mAP Representations and Coding-Based Priors for Segmentation}},
  author    = {Keeler, Kenneth},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {420-425},
  doi       = {10.1109/CVPR.1991.139727},
  url       = {https://mlanthology.org/cvpr/1991/keeler1991cvpr-map/}
}