Adaptive level set model based on local and global intensity information for image segmentation

In view of the problem that only using local or global intensity information cannot quickly and accurately segment images with intensity inhomogeneity, an adaptive level set model based on local and global intensity information is proposed for image segmentation. Firstly, by using local and global intensity information of image to establish the local and global energy term, and using intensity difference between the inner and the outer contour of the small neighborhood to establish weighting function, we realize adaptive adjustment of the weight between the local and global energy term, and greatly improve the efficiency and accuracy of the segmentation result. Secondly, we propose a novel energy penalty term, which avoids the re-initialization of the level set function and enhances the stability of the numerical calculation. Finally, in order to verify the superiority of the proposed model, we compare the proposed model with CV model, LBF model and LGIF model and make an objective and quantitative analysis by using the time of segmentation, the number of iterations and the similarity value. The final results show that the proposed model not only has high robustness to the initial contours, but also has high segmentation accuracy and segmentation efficiency for the images with intensity inhomogeneity.