Detection of glaucoma using retinal fundus images

This paper proposes an image processing technique for the detection of glaucoma which mainly affects the optic disc by increasing the cup size. During early stages it was difficult to detect Glaucoma, which is in fact second leading cause of blindness. In this paper glaucoma is categorized through extraction of features from retinal fundus images. The features include (i) Cup to Disc Ratio (CDR), which is one of the primary physiological parameter for the diagnosis of glaucoma and (ii) Ratio of Neuroretinal Rim in inferior, superior, temporal and nasal quadrants i.e. (ISNT quadrants) for verification of the ISNT rule. The novel technique is implemented on 80 retinal images and an accuracy of 97.5% is achieved taking an average computational time of 0.8141 seconds.