ML Anthology

Non-Parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval

Jan Puzicha, Thomas Hofmann, Joachim M. Buhmann
CVPR 1997 pp. 267-272
doi:10.1109/CVPR.1997.609331 /cvpr/1997/puzicha1997cvpr-non/

Abstract

In this paper we propose and examine non-parametric statistical tests to define similarity and homogeneity measures for textures. The statistical tests are applied to the coefficients of images filtered by a multi-scale Gabor filter bank. We demonstrate that these similarity measures are useful for both, texture based image retrieval and for unsupervised texture segmentation, and hence offer a unified approach to these closely related tasks. We present results on Brodatz-like micro-textures and a collection of real-word images.

CVPR Semantic Scholar

Cite

Text

Puzicha et al. "Non-Parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609331

Markdown

[Puzicha et al. "Non-Parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/puzicha1997cvpr-non/) doi:10.1109/CVPR.1997.609331

BibTeX

@inproceedings{puzicha1997cvpr-non,
  title     = {{Non-Parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval}},
  author    = {Puzicha, Jan and Hofmann, Thomas and Buhmann, Joachim M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {267-272},
  doi       = {10.1109/CVPR.1997.609331},
  url       = {https://mlanthology.org/cvpr/1997/puzicha1997cvpr-non/}
}