Data Mining Approach: Distribution of Retinal Plasma Liner Handling Image Processing for Automated Retinal Analysis Kannan M.1, Prasanna D.2 1Professor Department of Computer Science Engineering, Mahendra Engineering College (Autonomous), Namakkal, Tamilnadu, India 2Assistant Professor, Department of Computer Science Engineering, Mahendra Engineering College (Autonomous), Namakkal, Tamilnadu, India Online published on 16 March, 2018. Abstract Computed Aided Diagnosis (CAD) methods are highly used by the medical professionals in the field of medical image analysis. Many retinal diseases like retinopathy, occlusion etc. are identified through the changes occur in the retinal vasculature of fundus images. Detection of glaucoma at early stages is essential to avoid the sight-threatening retinal disease. In this paper, the data mining techniques based on retinal image analysis by means of blood vessel segmentation done by the image processing method is discussed in this paper. the work involves the steps like channel separation from the input images and the optic Disc (oD) segmentation by means of the Fuzzy C-Means (FCM) algorithm, followed by the extraction of features from the segmented images. Now the data mining steps like feature selection and the classification process are done by using the K-Nearest Neighbor (KNN) classifier is expressed. The performance accuracy of glaucoma detection is obtained at the maximum of 97.2%. Top Keywords Retinal, Glaucoma, Fundus, FCM, KNN classifier. Top |