ML Anthology

Gabor Filter Analysis for Texture Segmentation

Roman Sandler, Michael Lindenbaum
CVPRW 2006 pp. 178
doi:10.1109/CVPRW.2006.86 /cvprw/2006/sandler2006cvprw-gabor/

Abstract

Gabor features are a common choice for texture analysis. The particular set of Gabor filters used for extracting the features is usually designed for optimal signal representation. We propose here an alternative criterion for designing the filter set. We consider a set of filters and its response to pairs of harmonic signals. Two signals are considered separable if the corresponding two sets of vector responses are disjoint in at least one of the components. We look for the set of Gabor filters that maximizes the fraction of separable harmonic signal pairs. The resulting filters are significantly different from the traditional ones. We test these maximal harmonic discrimination (MHD) filters using two texture discrimination methods, and describe their advantages over traditional filters.

CVPRW Semantic Scholar

Cite

Text

Sandler and Lindenbaum. "Gabor Filter Analysis for Texture Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006. doi:10.1109/CVPRW.2006.86

Markdown

[Sandler and Lindenbaum. "Gabor Filter Analysis for Texture Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006.](https://mlanthology.org/cvprw/2006/sandler2006cvprw-gabor/) doi:10.1109/CVPRW.2006.86

BibTeX

@inproceedings{sandler2006cvprw-gabor,
  title     = {{Gabor Filter Analysis for Texture Segmentation}},
  author    = {Sandler, Roman and Lindenbaum, Michael},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2006},
  pages     = {178},
  doi       = {10.1109/CVPRW.2006.86},
  url       = {https://mlanthology.org/cvprw/2006/sandler2006cvprw-gabor/}
}