On the Perceptual Organization of Texture and Shading Flows: From a Geometrical Model to Coherence Computation

Ben-Shahar, Ohad; Zucker, Steven W.

doi:10.1109/CVPR.2001.990646

On the Perceptual Organization of Texture and Shading Flows: From a Geometrical Model to Coherence Computation

Ohad Ben-Shahar, Steven W. Zucker

CVPR 2001 pp. I:1048-1055

doi:10.1109/CVPR.2001.990646 /cvpr/2001/benshahar2001cvpr-perceptual/

Abstract

Locally parallel dense patterns - sometimes called texture flows define a perceptually coherent structure which is important to image segmentation, edge classification, shading analysis, and shape interpretation. This paper develops the notion of texture flow from a geometrical point of view to argue that local measurements of such structures must incorporate two curvatures. We show how basic theoretical considerations lead to a unique model for the local behavior of the flow and allow for the specification of consistency constraints between nearby measurements. The computation of globally coherent structure via neighborhood relationships is demonstrated on synthetic and natural images, and is compared to orientation diffusion.

CVPR Semantic Scholar

Cite

Text

Ben-Shahar and Zucker. "On the Perceptual Organization of Texture and Shading Flows: From a Geometrical Model to Coherence Computation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990646

Markdown

[Ben-Shahar and Zucker. "On the Perceptual Organization of Texture and Shading Flows: From a Geometrical Model to Coherence Computation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/benshahar2001cvpr-perceptual/) doi:10.1109/CVPR.2001.990646

BibTeX

@inproceedings{benshahar2001cvpr-perceptual,
  title     = {{On the Perceptual Organization of Texture and Shading Flows: From a Geometrical Model to Coherence Computation}},
  author    = {Ben-Shahar, Ohad and Zucker, Steven W.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:1048-1055},
  doi       = {10.1109/CVPR.2001.990646},
  url       = {https://mlanthology.org/cvpr/2001/benshahar2001cvpr-perceptual/}
}