Glaucoma detection through optic disc and cup segmentation using K-mean clustering

One of the primary cause of blindness is Glaucoma. Although the disease is incurable but its symptoms can be minimized therefore early detection of the disease is essential. Elevated intraocular pressure, gradual vision loss which is a step towards blindness, structural damage to the retina are the marked symptoms of Glaucoma. Manually. It is diagnosed by examination of size, structure, shape of optic disc and optic cup. In patient of glaucoma Cup size increases while disc area remains the same hence cup to disc ratio (CDR) increases in glaucoma patient. CDR is the ratio of optic cup area to the optic disc area, which provides basis for the diagnosis of glaucoma. This article focuses on automated detection of glaucoma from fundus images using CDR. Region of interest (ROI) extraction through intensity weighted centroid method which is followed by preprocessing and recursively applied k-mean clustering segmentation for the detection of Optic cup (OC) and optic disc (OD). Ellipse fitting is implied for boundary smoothening of OC and OD. Performance of the proposed technique is assessed on 100 fundus images collected locally. Proposed approach gives an accuracy of 92% for glaucoma and Mean square error of 0.002 for CDR.