A spatially continuous max-flow and min-cut framework for binary labeling problems |
| |
Authors: | Jing Yuan Egil Bae Xue-Cheng Tai Yuri Boykov |
| |
Institution: | 1. Computer Science Department, Middlesex College, University of Western Ontarion, London, ON, N6A 5B7, Canada 2. Department of Mathematics, University of California, Los Angeles, CA, USA 3. Department of Mathematics, University of Bergen, Bergen, Norway
|
| |
Abstract: | We propose and investigate novel max-flow models in the spatially continuous setting, with or without i priori defined supervised constraints, under a comparative study of graph based max-flow/min-cut. We show that the continuous max-flow models correspond to their respective continuous min-cut models as primal and dual problems. In this respect, basic conceptions and terminologies from discrete max-flow/min-cut are revisited under a new variational perspective. We prove that the associated nonconvex partitioning problems, unsupervised or supervised, can be solved globally and exactly via the proposed convex continuous max-flow and min-cut models. Moreover, we derive novel fast max-flow based algorithms whose convergence can be guaranteed by standard optimization theories. Experiments on image segmentation, both unsupervised and supervised, show that our continuous max-flow based algorithms outperform previous approaches in terms of efficiency and accuracy. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|