A new image segmentation method based On 3-dimensional entropic thresholding using a 3-dimensional (GLLALE) histogram

Thresholding is an an essential step in processing digital images for many applications. Accurate thresholding of digital images is crucial and the objective of this study is to develop a more accurate solution for estimating the optimal threshold value of digital images. This paper proposes a 3-dimensional entropic thresholding method based on a 3-dimensional histogram (GLLALE). The proposed method was applied on several test images and promising results were obtained. Evaluation of the resulting segmented images shows that the proposed method yields better estimation of the optimal threshold than does the 1D entropic thresholding of Kapur, and the 2D entropic thresholding methods of Abutaleb and Xiao.