Detection of Glaucomatous Eye via Color Fundus Images Using Fractal Dimensions

Abstract

This paper describes a method for glaucomatous eye detection based on fractal description, followed by classification. Two methods for fractal dimensions estimation, which give a different image/tissue description, are presented. The fundus color images are used, in which the areas with retinal nerve fibers are analyzed. The presented method shows that fractal dimensions can be used as features for retinal nerve fibers losses detection, which is a sign of glaucomatous eye.