Fast Continuous Max-Flow Algorithm to 2D/3D Multi-Region Image Segmentation

It implements the fast continuous max-flow algorithm to 2D/3D multi-region image segmentation.

This software implements the fast continuous max-flow algorithm to 2D/3D multi-region image segmentation (Potts model). It provides three implementations: matlab, C and GPU (cuda based). All the source files are provided. So it is easy for you to incorporate the algorithms in your own applications.

2D/3D multi-region image segmentation can be modeled as computing the multi-way cuts, i.e. Potts model, in the spatially continuous setting, and solved by its convex relaxation. The continuous max-flow formulation is dual/equivalent to such convex relaxed Potts model problem. On the other hand, it also leads to a new fast algorithm in numerics, i.e. the fast continuous max-flow algorithm. More details are given in the document CMFML_README.pdf. Wish this software would be helpful for you and your works!

For image segmentation with two regions: foreground and background, the fast continuous max-flow algorithm can be downloaded through:
http://www.mathworks.com/matlabcentral/fileexchange/34126
which is simpler.

Email Jing Yuan ([e-mail]) for the questions, comments and suggests. You are welcome to propose your ideas of improvements. Any contribution will be kindly acknowledged in CMFML_README.pdf.