Image Segmentation Based on the Self-Balancing Mechanism in Virtual 3D Elastic Mesh

TL;DR

This paper introduces a novel 3D elastic mesh model with a self-balancing mechanism for image segmentation, inspired by physical elastic objects, demonstrating stability and effectiveness in segmenting both test and real-world images.

Contribution

The paper proposes a new 3D elastic mesh model with a self-balancing mechanism tailored for image segmentation, enhancing stability and segmentation accuracy.

Findings

Effective segmentation of test images

Successful application to real-world images

Stable segmentation process due to self-balancing mechanism

Abstract

In this paper, a novel model of 3D elastic mesh is presented for image segmentation. The model is inspired by stress and strain in physical elastic objects, while the repulsive force and elastic force in the model are defined slightly different from the physical force to suit the segmentation problem well. The self-balancing mechanism in the model guarantees the stability of the method in segmentation. The shape of the elastic mesh at balance state is used for region segmentation, in which the sign distribution of the points'z coordinate values is taken as the basis for segmentation. The effectiveness of the proposed method is proved by analysis and experimental results for both test images and real world images.