High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Automatic Delineation Of Retinal Area From SLO Images For Diagnosing Diabetic Retinopathy

Author(s):

Ajitha.S , K M P College of Engineering; Akhil S, K M P College of Engineering

Keywords:

Diabetic Retinopathy (DR), Gray level co- occurrence matrix (GLCM), Proliferative Diabetic Retinopathy (PDR), Non-proliferative diabetic retinopathy (NPDR), Super Pixels, Scanning Laser ophthalmoscope (SLOs), Simple linear Iterative clustering (SLIC), Support Vector Machine(SVM)

Abstract

Diabetic retinopathy is one of the leading impairing chronic diseases and one of the leading causes of preventable blindness in the world. Most of the ophthalmologist depends on the visual interpretation for the identification of Diabetic Retinopathy. But incorrect diagnosis will change the course of treatment planning which leads to fatal results. Hence there is a requirement for a impartial automated system which gives highly accurate results. Early diagnosis of diabetic retinopathy enables timely treatment. To achieve this a major effort will have to be invested into automated screening programs. For automatic screening programs to work vigorously efficient image processing and analysis algorithms have to be developed. Nowadays, Scanning laser ophthalmoscopes (SLOs) can be used for detection of retinal diseases. In this paper, we propose a novel framework for the extraction of retinal area of SLO images and diagnosis of retinal diseases from the retinal area using Support vector machine. The proposed method analyze the retinal images for important features of diabetic retinopathy using image processing techniques and an image classifier based on SVM which classify the images conforming to disease conditions. The main types of diabetic retinopathy are non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR).

Other Details

Paper ID: IJSRDV4I60444
Published in: Volume : 4, Issue : 6
Publication Date: 01/09/2016
Page(s): 859-863

Article Preview

Download Article