A linear framework for region-based image segmentation and inpainting involving curvature penalization

TL;DR

This paper introduces a novel linear programming framework for region-based image segmentation and inpainting that incorporates curvature regularity, improving results especially for long, thin structures and being independent of initialization.

Contribution

It presents the first curvature-regularized segmentation and inpainting method formulated as an integer linear program, extending length-based schemes with a new curvature constraint.

Findings

Curvature regularity improves segmentation of long, thin objects.

Linear programming relaxation yields near-optimal solutions.

Method is initialization-independent.

Abstract

We present the first method to handle curvature regularity in region-based image segmentation and inpainting that is independent of initialization. To this end we start from a new formulation of length-based optimization schemes, based on surface continuation constraints, and discuss the connections to existing schemes. The formulation is based on a \emph{cell complex} and considers basic regions and boundary elements. The corresponding optimization problem is cast as an integer linear program. We then show how the method can be extended to include curvature regularity, again cast as an integer linear program. Here, we are considering pairs of boundary elements to reflect curvature. Moreover, a constraint set is derived to ensure that the boundary variables indeed reflect the boundary of the regions described by the region variables. We show that by solving the linear programming relaxation one gets quite close to the global optimum, and that curvature regularity is indeed much better suited in the presence of long and thin objects compared to standard length regularity.