ML Anthology

A Framework for Segmentation Using Physical Models of Image Formation

Bruce A. Maxwell, Steven A. Shafer
CVPR 1994 pp. 361-368
doi:10.1109/CVPR.1994.323852 /cvpr/1994/maxwell1994cvpr-framework/

Abstract

This paper presents a new approach to segmentation using explicit hypotheses about the physics that creates images. We propose an initial segmentation that identifies image regions exhibiting constant color; but possibly varying intensity. For each region, we propose a set of hypotheses, each of which specifically models the illumination, reflectance, and shape of the 3-D patch which caused that region. Each hypothesis represents a distinct, plausible explanation for the color and intensity variation of that patch. Hypotheses for adjacent patches can be compared for similarity and merged when appropriate, resulting in more global hypotheses which group elementary regions.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Maxwell and Shafer. "A Framework for Segmentation Using Physical Models of Image Formation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323852

Markdown

[Maxwell and Shafer. "A Framework for Segmentation Using Physical Models of Image Formation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/maxwell1994cvpr-framework/) doi:10.1109/CVPR.1994.323852

BibTeX

@inproceedings{maxwell1994cvpr-framework,
  title     = {{A Framework for Segmentation Using Physical Models of Image Formation}},
  author    = {Maxwell, Bruce A. and Shafer, Steven A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {361-368},
  doi       = {10.1109/CVPR.1994.323852},
  url       = {https://mlanthology.org/cvpr/1994/maxwell1994cvpr-framework/}
}