Comparison Study of Two Energy Minimization Based Image Segmentation Methods

In this paper, two energy minimization based image segmentation methods are investigated. The formulations of both methods-level set and Otsu thresholding-are detailed. Several experiments are carried out and the comparison is conducted in terms of segmentation results, CPU time cost and adaptability to multi-phase images. The pros and cons of the methods are also discussed. As a by-product, we propose a variational explanation for Otsu thresholding method, which was initially introduced on the basis of discriminant criterion, namely, to maximize the separability of the resultant classes in gray levels.