A supervised machine learning algorithm SKVMs used for both classification and screening of glaucoma disease

Glaucoma is the second leading cause of vision loss in the world. We propose a novel, automated, appearance-based glaucoma classification system that does depend on segmentation-based measurements. It applies a standard pattern recognition process with a 2-stage classification step: To automatically extract the optic disc (OD), two methods making use of an edge detection method and Contours active Chan and Vese model are proposed in this paper. For the optic cup (OC) or excavation, inspection by the histogram is used to automatically detect the (OC). Our system SKVMs technique achieves 93% success rate on a data set containing a mixture of 75 real images of healthy and glaucomatous eyes. A set of 75 retinal images obtained from healthy and glaucomatous eyes, is used to assess the performance of the determined CDR to the clinical CDR, and it is found that our proposed method provides 98% accuracy in the determined CDR results and an early screening glaucoma by SKVMs approach that presented the aim of this paper.