Classification Approach for Diabetic Retinopathy Detection

An image is known as scalar in case if a single measurement is done at every location that exists in the image. Due to the development of high-speed, more accurate and less invasive devices, the medical imaging has been going through a revolution over the decade. Adequate software is also needed to be developed to handle such high level of imaging. The retinal images are evaluated to diagnose the DR. It is however, time consuming and resource demanding to manually grade the images such that the severity of DR can be defined. The KNN Classifier algorithm is implemented in MATLAB and results are analyzed in terms of accuracy, specificity and sensitivity. It is analyzed that KNN Classifier method performs well in terms accuracy, specificity and sensitivity as compared to SVM Classifier method.