Color Constant Ratio Gradients for Image Segmentation and Similarity of Texture Objects

Gevers, Theo; Smeulders, Arnold W. M.

doi:10.1109/CVPR.2001.990451

Color Constant Ratio Gradients for Image Segmentation and Similarity of Texture Objects

Theo Gevers, Arnold W. M. Smeulders

CVPR 2001 pp. I:18-25

doi:10.1109/CVPR.2001.990451 /cvpr/2001/gevers2001cvpr-color/

Abstract

We aim for content-based image retrieval of texture objects in natural scenes under varying illumination and viewing conditions. To achieve this, image retrieval is based on matching feature distributions derived from color invariant gradients. To cope with object cluttering, region-based texture segmentation is applied on the target images prior to the actual image retrieval process. The retrieval scheme is empirically verified on color images taken from texture objects under different lighting, conditions.

CVPR Semantic Scholar

Cite

Text

Gevers and Smeulders. "Color Constant Ratio Gradients for Image Segmentation and Similarity of Texture Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990451

Markdown

[Gevers and Smeulders. "Color Constant Ratio Gradients for Image Segmentation and Similarity of Texture Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/gevers2001cvpr-color/) doi:10.1109/CVPR.2001.990451

BibTeX

@inproceedings{gevers2001cvpr-color,
  title     = {{Color Constant Ratio Gradients for Image Segmentation and Similarity of Texture Objects}},
  author    = {Gevers, Theo and Smeulders, Arnold W. M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:18-25},
  doi       = {10.1109/CVPR.2001.990451},
  url       = {https://mlanthology.org/cvpr/2001/gevers2001cvpr-color/}
}