A variable gaussian kernel scale active contour model based on Jeffreys divergence for ICT image segmentation

Abstract

In industrial computed tomography (ICT), factors like beam scattering, insufficient beam intensity, and detector dark current often lead to weak edges, scattering artifacts, and severe Gaussian noise in ICT images. These issues pose significant difficulties for accurate segmentation of high-density complex structures using existing active contour models (ACMs). To address these limitations, this paper presents a variable Gaussian kernel scale active contour model based on Jeffreys divergence (VGJD). Firstly, the Jeffreys divergence (JD) is incorporated into the energy function to replace the conventional Euclidean distance, enhancing the contour’s ability to quantify pixel value disparity during evolution. Additionally, a filter weight is introduced to minimize the impact of noise. Moreover, a variable Gaussian kernel scale strategy is adopted to effectively integrate both global and local image information, thereby enhancing the robustness of the initial contour and improving the precision of detail segmentation. Finally, optimized length and regularity terms are employed to enforce constraints on the level set function. Extensive experimental results demonstrate that the VGJD model can effectively segment various complex ICT images, achieving superior precision in comparison to other ACM models. The code is available at https://github.com/LiuZX599/ACM-VGJD.git