Segmentation of medical images using Selective Binary and Gaussian Filtering regularized level set (SBGFRLS) method

摘要

This paper implements the Selective Binary and Gaussian Filtering regularized level set (SBGFRLS) method for segmentation of medical images. The SBGFRLS is a region based active contour model. The advantages of this method is as follows. Firstly, the signed pressure function(SPF) can efficiently stop the contours at weak or blurred edges. Secondly, exterior and interior boundaries can be detected no matter where the initial contour starts. Experiments on medical images demonstrates the utility of this method. Finally, we have shown the relation between a and number of iterations required in the algorithm to get optimal result.