Interactive Image Segmentation Using Constrained Dominant Sets

@inproceedings{Mequanint2016InteractiveIS,
  title={Interactive Image Segmentation Using Constrained Dominant Sets},
  author={Eyasu Zemene Mequanint and Marcello Pelillo},
  booktitle={ECCV},
  year={2016}
}
We propose a new approach to interactive image segmentation based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster which generalizes the concept of a maximal clique to edge-weighted graphs. In particular, we show that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, we are in a position to extract groups of dominant-set clusters… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 9 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 21 extracted citations

Intelligent Data Engineering and Automated Learning – IDEAL 2017

Lecture Notes in Computer Science • 2017
View 4 Excerpts
Highly Influenced

Probabilistic Diffusion for Interactive Image Segmentation

IEEE Transactions on Image Processing • 2019
View 2 Excerpts

Dominant Sets for "Constrained" Image Segmentation

IEEE transactions on pattern analysis and machine intelligence • 2018
View 1 Excerpt

Large-scale Image Geo-Localization Using Dominant Sets

IEEE transactions on pattern analysis and machine intelligence • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 41 references

Loosecut: Interactive image segmentation with loosely bounded boxes

2017 IEEE International Conference on Image Processing (ICIP) • 2017
View 11 Excerpts
Highly Influenced

Error-Tolerant Scribbles Based Interactive Image Segmentation

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 5 Excerpts
Highly Influenced

Image segmentation with a bounding box prior

2009 IEEE 12th International Conference on Computer Vision • 2009
View 8 Excerpts
Highly Influenced

MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 10 Excerpts
Highly Influenced

Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation

2013 IEEE International Conference on Computer Vision • 2013
View 3 Excerpts
Highly Influenced

Geodesic graph cut for interactive image segmentation

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition • 2010
View 5 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…