ML Anthology

Texture-Based Image Retrieval Without Segmentation

Yossi Rubner, Carlo Tomasi
ICCV 1999 pp. 1018-1024
doi:10.1109/ICCV.1999.790380 /iccv/1999/rubner1999iccv-texture/

Abstract

Image segmentation is not only hard and unnecessary for texture-based image retrieval, but can even be harmful. Images of either individual or multiple textures are best described by distributions of spatial frequency descriptors, rather than single descriptor vectors over presegmented regions. A retrieval method based on the earth movers distance with an appropriate ground distance is shown to handle both complete and partial multi-textured queries. As an illustration, different images of the same type of animal are easily retrieved together. At the same time, animals with subtly different coats, like cheetahs and leopards, are properly distinguished.

ICCV Semantic Scholar

Cite

Text

Rubner and Tomasi. "Texture-Based Image Retrieval Without Segmentation." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.790380

Markdown

[Rubner and Tomasi. "Texture-Based Image Retrieval Without Segmentation." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/rubner1999iccv-texture/) doi:10.1109/ICCV.1999.790380

BibTeX

@inproceedings{rubner1999iccv-texture,
  title     = {{Texture-Based Image Retrieval Without Segmentation}},
  author    = {Rubner, Yossi and Tomasi, Carlo},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {1018-1024},
  doi       = {10.1109/ICCV.1999.790380},
  url       = {https://mlanthology.org/iccv/1999/rubner1999iccv-texture/}
}