Interactive image segmentation via kernel propagation

  title={Interactive image segmentation via kernel propagation},
  author={Zhendong Zhang and Meng Jian and Juan Liu and Licheng Jiao and Yanbo Shen},
  journal={Pattern Recognition},
In this paper, we propose a new approach to interactive image segmentation via kernel propagation (KP), called KP Cut. The key to success in interactive image segmentation is to preserve characteristics of the user's interactive input and maintain data-coherence effectively. To achieve this, we employ KP which is very effective in propagating the given supervised information into the entire data set. KP first learns a small-size seed-kernel matrix, and then propagates it into a large-size full… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 31 references

Semisupervised Kernel Matrix Learning by Kernel Propagation

IEEE Transactions on Neural Networks • 2010
View 4 Excerpts
Highly Influenced

Lazy snapping

ACM Trans. Graph. • 2004
View 10 Excerpts
Highly Influenced

A Bayesian Network Model for Automatic and Interactive Image Segmentation

IEEE Transactions on Image Processing • 2011
View 1 Excerpt

Similar Papers

Loading similar papers…