ML Anthology

Smooth Region Structure: Folds, Domes, Bowls, Ridges, Valleys and Slopes

David Sinclair
CVPR 2000 pp. 1389-1394
doi:10.1109/CVPR.2000.855845 /cvpr/2000/sinclair2000cvpr-smooth/

Abstract

This paper shows that the structure of the isobrightness contours in 'smooth' regions of a segmented image may be used to quantify the variation in shading. Topographic terms are then appropriate for labelling the kinds of generic structure that arise in smooth region domes, bowls, ridges, valleys, slopes and folds are quantifiable. The method uses contour context rather that filter banks or a solution to the shape from shading problem to quality the form of a region's brightness function. Region segmentation (distinguishing smooth from textured regions) is also performed with a largely filter free segmentation scheme with a brief outline of the scheme being given.

CVPR Semantic Scholar

Cite

Text

Sinclair. "Smooth Region Structure: Folds, Domes, Bowls, Ridges, Valleys and Slopes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855845

Markdown

[Sinclair. "Smooth Region Structure: Folds, Domes, Bowls, Ridges, Valleys and Slopes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/sinclair2000cvpr-smooth/) doi:10.1109/CVPR.2000.855845

BibTeX

@inproceedings{sinclair2000cvpr-smooth,
  title     = {{Smooth Region Structure: Folds, Domes, Bowls, Ridges, Valleys and Slopes}},
  author    = {Sinclair, David},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1389-1394},
  doi       = {10.1109/CVPR.2000.855845},
  url       = {https://mlanthology.org/cvpr/2000/sinclair2000cvpr-smooth/}
}