Detection of Diabetic Retinopathy Through Identification of Blood Vessel Thickness Using-FOFF

Abstract

Diabetes is one of the main problems in today's medical industry. Identification and diagnosis of the eye condition brought on by diabetes' elevated blood sugar levels are crucial. The motive of the work is to present a useful technique for system diagnosis utilizing a retinal fundus picture. A four-stage implementation paradigm is created in this study. Initially the input image is pre-processed, secondly blood vessel segmentation is performed; thirdly feature extraction and finally classification. In this paper an effective methodology is utilized by introducing meta heuristic algorithm. In the entire process, blood vessel segmentation (BVS)contributes a crucial part in DR detection for which a firefly optimized frangi filter (FOFF) is designed in this paper. The process of categorization comes last. The classifiers K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are employed. The performance of system is evaluated by computing the accuracy and precision. The results are compared between the two utilized classifiers. The SVM performance is good with an accuracy of 95.5% and KNN having an accuracy of 91.6%.