Glaucoma Detection from Color Fundus Images Using Multithresholding Method with Median Filter

Abstract

Glaucoma is a pathological condition, progressive neurodegeneration of the optic nerve, which causes vision loss. The damage to the optic nerve occurs due to the increase in pressure within the eye. Glaucoma is evaluated by monitoring intra ocular pressure (IOP), visual field and the optic disc appearance (cup-to-disc ratio). Cup-to disc ratio (CDR) is normally a time invariant feature. Therefore, it is one of the most accepted indicators of this disease and the disease progression. In this paper, Multi thresholding method with median filter is used to find the CDR from the color fundus images to determine pathological process of glaucoma. The method is applied on 25 nos of color fundus images obtained from optic disc organization UK having normal and pathological images. The proposed technique able to categorize all the glaucoma disease images.