ML Anthology

Unsupervised Local Color Correction for Coarsely Registered Images

Miguel Oliveira, Angel Domingo Sappa, Vítor M. F. Santos
CVPR 2011 pp. 201-208
doi:10.1109/CVPR.2011.5995658 /cvpr/2011/oliveira2011cvpr-unsupervised/

Abstract

The current paper proposes a new parametric local color correction technique. Initially, several color transfer functions are computed from the output of the mean shift color segmentation algorithm. Secondly, color influence maps are calculated. Finally, the contribution of every color transfer function is merged using the weights from the color influence maps. The proposed approach is compared with both global and local color correction approaches. Results show that our method outperforms the technique ranked first in a recent performance evaluation on this topic. Moreover, the proposed approach is computed in about one tenth of the time.

CVPR Semantic Scholar

Cite

Text

Oliveira et al. "Unsupervised Local Color Correction for Coarsely Registered Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995658

Markdown

[Oliveira et al. "Unsupervised Local Color Correction for Coarsely Registered Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/oliveira2011cvpr-unsupervised/) doi:10.1109/CVPR.2011.5995658

BibTeX

@inproceedings{oliveira2011cvpr-unsupervised,
  title     = {{Unsupervised Local Color Correction for Coarsely Registered Images}},
  author    = {Oliveira, Miguel and Sappa, Angel Domingo and Santos, Vítor M. F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {201-208},
  doi       = {10.1109/CVPR.2011.5995658},
  url       = {https://mlanthology.org/cvpr/2011/oliveira2011cvpr-unsupervised/}
}