Title :
Submodularity beyond submodular energies: Coupling edges in graph cuts
Author :
Jegelka, Stefanie ; Bilmes, Jeff
Author_Institution :
Max Planck Inst. Tubingen, Germany
Abstract :
We propose a new family of non-submodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We demonstrate the advantages of edge coupling in a natural setting, namely image segmentation. In particular, for fine-structured objects and objects with shading variation, our structured edge coupling leads to significant improvements over standard approaches.
Keywords :
approximation theory; graph theory; image segmentation; approximation algorithm; edge coupling; fine structured objects; graph cuts; image segmentation; nonsubmodular global energy functions; shading variation; submodular energies; Approximation algorithms; Approximation methods; Computer vision; Couplings; Image edge detection; Image segmentation; Labeling;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995589