Boundary Detection in Piecewise Homogeneous Textured Images
Abstract
We address the problem of scale selection in texture analysis. Two different scale parameters, feature scale and statistical scale, are defined. Statistical scale is the size of the regions used to compute averages. We define the class of homogeneous random functions as a model of texture. A dishomogeneity function is defined and we prove that it has useful asymptotic properties in the limit of infinite statistical scale. We describe an algorithm for image partitioning which has performed well on piecewise homogeneous synthetic images. This algorithm is embedded in a redundant pyramid and does not require any ad-hoc information. It selects the optimal statistical scale at each location in the image.
Cite
Text
Casadei et al. "Boundary Detection in Piecewise Homogeneous Textured Images." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_20Markdown
[Casadei et al. "Boundary Detection in Piecewise Homogeneous Textured Images." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/casadei1992eccv-boundary/) doi:10.1007/3-540-55426-2_20BibTeX
@inproceedings{casadei1992eccv-boundary,
title = {{Boundary Detection in Piecewise Homogeneous Textured Images}},
author = {Casadei, Stefano and Mitter, Sanjoy K. and Perona, Pietro},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {174-183},
doi = {10.1007/3-540-55426-2_20},
url = {https://mlanthology.org/eccv/1992/casadei1992eccv-boundary/}
}