A Local Active Contour Model for Image Segmentation with Intensity Inhomogeneity

TL;DR

This paper introduces a new local active contour model that effectively segments images with intensity inhomogeneity by modeling objects as Gaussian distributions and using a moving window to improve separation.

Contribution

The proposed model adaptively estimates Gaussian parameters in a transformed domain, enhancing segmentation accuracy in inhomogeneous images compared to existing methods.

Findings

Outperforms state-of-the-art segmentation algorithms on synthetic images.

Demonstrates robustness on real-world images with intensity inhomogeneity.

Effectively models inhomogeneous objects as Gaussian distributions.

Abstract

A novel locally statistical active contour model (ACM) for image segmentation in the presence of intensity inhomogeneity is presented in this paper. The inhomogeneous objects are modeled as Gaussian distributions of different means and variances, and a moving window is used to map the original image into another domain, where the intensity distributions of inhomogeneous objects are still Gaussian but are better separated. The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field with the original signal within the window. A statistical energy functional is then defined for each local region, which combines the bias field, the level set function, and the constant approximating the true signal of the corresponding object. Experiments on both synthetic and real images demonstrate the superiority of our proposed algorithm to state-of-the-art and representative methods.