Iterative graph cuts for image segmentation with a nonlinear statistical shape prior

TL;DR

This paper introduces an iterative graph cut method for image segmentation that incorporates nonlinear statistical shape priors, enabling efficient optimization of complex shape-based regularization in noisy images.

Contribution

It presents a novel approach to reformulate kernel density estimation-based shape priors into a form suitable for graph cut optimization, facilitating practical segmentation.

Findings

Effective segmentation with nonlinear shape priors

Improved handling of noisy images

Efficient iterative optimization process

Abstract

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.