A Combined Method Of Fractal And GLCM Features For MRI And CT Scan Images Classification

摘要

Fractal analysis has been shown to be useful in image processing forcharacterizing shape and gray-scale complexity. The fractal feature is acompact descriptor used to give a numerical measure of the degree ofirregularity of the medical images. This descriptor property does not giveownership of the local image structure. In this paper, we present a combinationof this parameter based on Box Counting with GLCM Features. This powerfulcombination has proved good results especially in classification of medicaltexture from MRI and CT Scan images of trabecular bone. This method has thepotential to improve clinical diagnostics tests for osteoporosis pathologies.