Iterative graph cuts for image segmentation with a nonlinear statistical shape prior
This work addresses a computational bottleneck for researchers and practitioners in medical imaging or computer vision who use shape priors for noisy image segmentation, representing an incremental improvement.
The paper tackles the problem of efficiently minimizing energy functionals from kernel density estimation shape priors in image segmentation, which are incompatible with graph cuts, by reformulating them into an iteratively minimizable form using graph cuts.
Shape-based regularization has proven to be a useful method for delineating objects within noisy images where one has prior knowledge of the shape of the targeted object. When a collection of possible shapes is available, the specification of a shape prior using kernel density estimation is a natural technique. Unfortunately, energy functionals arising from kernel density estimation are of a form that makes them impossible to directly minimize using efficient optimization algorithms such as graph cuts. Our main contribution is to show how one may recast the energy functional into a form that is minimizable iteratively and efficiently using graph cuts.