Optic Cub Detection for Diagnosing Glaucoma using Neural Network

Abstract

Glaucoma is an important cause of vision failure in human being. In early stage, people cannot realize that they have reached the glaucoma stage. There will be no indication like pain or immediate loss of vision. Checking the top of optic nerve called cup-to-disc ratio is very important for diagnosing glaucoma. Images are acquired by fundus camera. The cup segmentation techniques are used to isolate the needed parts of the retinal image and to calculate the disc ratio. This research proposes an intelligent image processing method to detect glaucoma to help the ophthalmologist in screening glaucoma. The proposed approach is based on the segmentation of optic disk and the optic cup. Hough Transform is used to calculate the radius of the cup. The vertical cup to disk ratio is used for identification of glaucoma symptoms in the fundus image. The results of the proposed method indicate that the approach is effective in glaucoma detection with better accuracy over existing works.