Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement

TL;DR

This paper presents a novel image segmentation method using geodesic paths within an Eikonal PDE framework, integrating region homogeneity and edge features for improved boundary detection.

Contribution

It introduces a flexible model that incorporates implicit region homogeneity into local geodesic metrics, enhancing segmentation accuracy over existing minimal path methods.

Findings

Outperforms state-of-the-art minimal path segmentation methods

Effectively integrates anisotropic, asymmetric edge features and homogeneity

Builds simple closed contours from disjoint open curves

Abstract

Minimal paths are regarded as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and the well-established numerical solutions such as fast marching method. In this paper, we introduce a flexible interactive image segmentation model based on the Eikonal partial differential equation (PDE) framework in conjunction with region-based homogeneity enhancement. A key ingredient in the introduced model is the construction of local geodesic metrics, which are capable of integrating anisotropic and asymmetric edge features, implicit region-based homogeneity features and/or curvature regularization. The incorporation of the region-based homogeneity features into the metrics considered relies on an implicit representation of these features, which is one of the contributions of this work. Moreover, we also introduce a way to build simple closed contours as the concatenation of two disjoint open curves. Experimental results prove that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.