Semi-Supervised Segmentation based on Non-local Continuous Min-Cut

We propose a semi-supervised image segmentation method that relies on a non-local continuous version of the min-cut algorithm and labels or seeds provided by a user. The segmentation process is performed via energy minimization. The proposed energy is composed of three terms. The ¯rst term de¯nes labels or seed points assigned to objects that the user wants to identify and the background. The second term carries out the di®usion of object and background labels and stops the di®usion when the interface between the object and the background is reached. The di®usion process is performed on a graph de¯ned from image intensity patches. The graph of intensity patches is known to better deal with textures because this graph uses semi-local and non-local image information. The last term is the standard TV term that regularizes the geometry of the interface.We introduce an iterative scheme that provides a unique minimizer. Promising results are presented on synthetic textures a nd real-world images.


Published in:
Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision, 5567/2009, 112-123
Presented at:
2nd International Conference on Scale Space and Variational Methods in Computer Vision, Voss, Norway, June 1-5, 2009
Year:
2009
Publisher:
Springer
Keywords:
Laboratories:




 Record created 2009-03-24, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)