A variational framework combining level-sets and thresholding

Abstract

Segmentation involves separating distinct regions in an image. In this note, we present a novel variational approach to perform this task within the level-sets framework. We propose an energy functional that naturally combines two segmentation techniques usually applied separately: intensity thresholding and geometric active contours. Although our method can deal with more complex statistics, we assume that the pixel intensities of the regions have Gaussian distributions, in this work. The proposed approach affords interesting properties that can lead to sensible segmentation results.