A comparative study on entropic thresholding methods

Abstract

Image thresholding is an important task both for digital image processing applications and for pattern recognition. Image segmentation by thresholding is the simplest technique. In this study, we intent to carry out a comparative study of entropic thresholding methods. We examine several entropic thresholding methods which are the most popular in the literature. These methods are minimum cross entropy, maximum entropy sum method, Renyi's entropy and Havrda&Charvat entropy. We perform experiments for demonstrating the effectiveness of the examined methods on image thresholding.