Patch-Based Texture Edges and Segmentation
Abstract
A novel technique for extracting texture edges is introduced. It is based on the combination of two ideas: the patch-based approach, and non-parametric tests of distributions. Our method can reliably detect texture edges using only local information. Therefore, it can be computed as a preprocessing step prior to segmentation, and can be very easily combined with parametric deformable models. These models furnish our system with smooth boundaries and globally salient structures.
Cite
Text
Wolf et al. "Patch-Based Texture Edges and Segmentation." European Conference on Computer Vision, 2006. doi:10.1007/11744047_37Markdown
[Wolf et al. "Patch-Based Texture Edges and Segmentation." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/wolf2006eccv-patch/) doi:10.1007/11744047_37BibTeX
@inproceedings{wolf2006eccv-patch,
title = {{Patch-Based Texture Edges and Segmentation}},
author = {Wolf, Lior and Huang, Xiaolei and Martin, Ian and Metaxas, Dimitris N.},
booktitle = {European Conference on Computer Vision},
year = {2006},
pages = {481-493},
doi = {10.1007/11744047_37},
url = {https://mlanthology.org/eccv/2006/wolf2006eccv-patch/}
}