Title Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves
Authors Carl Olsson, Martin Byröd, Niels Christian Overgaard, Fredrik Kahl
Alternative Location http://dx.doi.org/10.1109/I..., Restricted Access
Publication Proceedings of 2009 IEEE 12th International Conference on Computer Vision (ICCV)
Year 2009
Pages 405 - 412
Document type Conference paper
Conference name 2009 IEEE 12th International Conference on Computer Vision (ICCV)
Conference Date 2009-09-29/2009-10-02
Conference Location Kyoto, Japan
Status Published
Quality controlled Yes
Language eng
Publisher IEEE
Abstract English The concept of graph cuts is by now a standard method for all sorts of low level vision problems. Its popularity is largely due to the fact that globally or near globally optimal solutions can be computed using efficient max flow algorithms. On the other hand it has been observed that this method may suffer from metrication errors. Recent work has begun studying continuous versions of graph cuts, which give smaller metrication errors. Another advantage is that continuous cuts are straightforward to parallelize. In this paper we extend the class of functionals that can be optimized in the continuous setting to include anisotropic TV-norms. We show that there is a so called coarea formula for these functionals making it possible to minimize them by solving a convex problem. We also show that the concept of α-expansion moves can be reformulated to fit the continuous formulation, and we derive approximation bounds in analogy with the discrete case. A continuous version of the Potts model for multi-class segmentation problems is presented, and it is shown how to obtain provably good solutions using continuous α-expansions.
ISBN/ISSN/Other ISBN: 978-1-4244-4419-9

Questions: webmaster
Last update: 2013-04-11

Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)