ML Anthology

Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs

Carsten Rother, Thomas P. Minka, Andrew Blake, Vladimir Kolmogorov
CVPR 2006 pp. 993-1000
doi:10.1109/CVPR.2006.91 /cvpr/2006/rother2006cvpr-cosegmentation/

Abstract

We introduce the term cosegmentation which denotes the task of segmenting simultaneously the common parts of an image pair. A generative model for cosegmentation is presented. Inference in the model leads to minimizing an energy with an MRF term encoding spatial coherency and a global constraint which attempts to match the appearance histograms of the common parts. This energy has not been proposed previously and its optimization is challenging and NP-hard. For this problem a novel optimization scheme which we call trust region graph cuts is presented. We demonstrate that this framework has the potential to improve a wide range of research: Object driven image retrieval, video tracking and segmentation, and interactive image editing. The power of the framework lies in its generality, the common part can be a rigid/non-rigid object (or scene), observed from different viewpoints or even similar objects of the same class.

CVPR Semantic Scholar

Cite

Text

Rother et al. "Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.91

Markdown

[Rother et al. "Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/rother2006cvpr-cosegmentation/) doi:10.1109/CVPR.2006.91

BibTeX

@inproceedings{rother2006cvpr-cosegmentation,
  title     = {{Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs}},
  author    = {Rother, Carsten and Minka, Thomas P. and Blake, Andrew and Kolmogorov, Vladimir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {993-1000},
  doi       = {10.1109/CVPR.2006.91},
  url       = {https://mlanthology.org/cvpr/2006/rother2006cvpr-cosegmentation/}
}