Comparison of global thresholding algorithms on rock joint images

Abstract

The paper stresses the study that deals with thresholding applied to a special domain rather than thresholding in general, because of (a) the general problem is rather unspecified, (b) there is a greater chance of evaluating thresholding algorithms, if limiting the domain of possible images, and (c) there is the application of interest to us. The content of this paper is (1) to compare the selected eight of widely used global thresholding algorithms for eight typical rock joint images; (2) based on the comparison, to see how they work for joint images, and (3) how to choose a global thresholding algorithm to segment the joint images with a small variable background (the background is not completely uniform). In order to evaluate these global algorithms, whatever how available they are for joint images, the algorithms have been implemented into a PC computer. After comparison of these algorithms, we modified optimal and between class variance algorithms for rock joint images. which makes thresholding more reasonable.