ML Anthology

Shape from Texture: The Homogeneity Hypothesis

Constantinos Marinos, Andrew Blake
ICCV 1990 pp. 350-353
doi:10.1109/ICCV.1990.139548 /iccv/1990/marinos1990iccv-shape/

Abstract

The authors show how a maximum likelihood estimator can be constructed for homogeneous texture. The estimator turns out to be strikingly simple. It simply enforces, iteratively, coincidence of the centroid of the observed elements with the centroid of the imaging window. Whereas the estimator is based on first moments, error bounds are obtained, the authors show, from second moments. Experiments indicate that, for real textures, orientation estimates fall well inside predicted bounds.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

ICCV Semantic Scholar

Cite

Text

Marinos and Blake. "Shape from Texture: The Homogeneity Hypothesis." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139548

Markdown

[Marinos and Blake. "Shape from Texture: The Homogeneity Hypothesis." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/marinos1990iccv-shape/) doi:10.1109/ICCV.1990.139548

BibTeX

@inproceedings{marinos1990iccv-shape,
  title     = {{Shape from Texture: The Homogeneity Hypothesis}},
  author    = {Marinos, Constantinos and Blake, Andrew},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {350-353},
  doi       = {10.1109/ICCV.1990.139548},
  url       = {https://mlanthology.org/iccv/1990/marinos1990iccv-shape/}
}