Multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity

Intensity inhomogeneity arising from the imperfect image acquisition process is a major challenge for image segmentation. Most of widely used image segmentation methods usually fail to segment the image with intensity inhomogeneity due to the assumption of intensity homogeneity. In this paper, an efficient multi-scale local region based level set method is proposed to segment the image with intensity inhomogeneity, which is based on the multi-scale segmentation and statistical analysis for intensities of local region. Firstly, the local region is defined in circular shape for capturing more local intensity information. The statistical analysis can be performed on intensities of local circular regions centered in each pixel by using multi-scale low-pass filtering. Then, the data term of level set energy functional can be constructed by approximating the normalized weighted image divided by multi-scale local intensity information in a piecewise constant way. In addition, the regularization term is built to control the smoothness of evolving curve and avoid the over-segmentation phenomenon and re-initialization step. Finally, the multi-scale segmentation is performed by minimizing the total level set energy functional by using the finite difference scheme. The experiments on synthetic and real images with slight or severe intensity inhomogeneity can demonstrate the efficiency and robustness of the proposed method. In addition, the comparisons with the recently popular local binary fitting (LBF) model and local Chan-Vese (LCV) model also show that our method has obvious superiority over the traditional local region based methods.