Shape Complexes in Continuous Max-Flow Hierarchical Multi-Labeling Problems

TL;DR

This paper introduces shape complexes for image segmentation that integrate hierarchical labels and geodesic star convexity constraints, enabling representation of complex shapes without coordinate warping.

Contribution

It presents a novel shape complex framework that combines hierarchical labels with geodesic star convexity, extending shape modeling in continuous max-flow segmentation.

Findings

Enables segmentation of more complex shapes.

Avoids ambiguous coordinate warping techniques.

Integrates hierarchical labels with shape constraints.

Abstract

Although topological considerations amongst multiple labels have been previously investigated in the context of continuous max-flow image segmentation, similar investigations have yet to be made about shape considerations in a general and extendable manner. This paper presents shape complexes for segmentation, which capture more complex shapes by combining multiple labels and super-labels constrained by geodesic star convexity. Shape complexes combine geodesic star convexity constraints with hierarchical label organization, which together allow for more complex shapes to be represented. This framework avoids the use of co-ordinate system warping techniques to convert shape constraints into topological constraints, which may be ambiguous or ill-defined for certain segmentation problems.