Literature Review On Diabetic Retinopathy

A REVIEW ON RETINAL FEATURE
SEGMENTATION METHODOLOGIES FOR

IABETIC RETINOPATHY
Dr. N. Jayalakshmi1 K. Priya2
HOD and Professor, Research Scholar,

Saveetha Engineering College, Research & Development Centre,

Chennai , India Bharathiar University, Coimbatore, India
Abstract--Diabetic Retinopathy is a most common diabetic

eye disease, which occurs when a blood vessel in the retina change. There are two stages of the disease. The early stage is

Non proliferative diabetic retinopathy (NPDR) and later is
Proliferative diabetic retinopathy (PDR). In NPDR, various problems may occur, such as macular edema which is

swelling in the central retina and retinal ischemia which occurs due to poor blood flow. PDR is the advanced stage of
NPDR, new blood

The RGB fundus image, gray scale image and CLAHE applied images are

shown in 2.1. (a) - 2.1.(c).

Figure 2.1:(a)Color fundus image, (b) Gray scale image,
(c) Enhanced image using CLAHE

2.2 All the images are commonly resized to [256 x
256] size. The image is divided into small regions. Median filter identifies the noisy pixels within the regions and

replace the noisy pixels with the median of the

neighbouring pixels within the regions. The RGB

component of the color input image was separated and pre- processed. Then pre-processed RGB components were

concatenated to obtain the filtered image. Figure 2.2 shows

the original fundus image and the pre-processed image.

Figure 2.2: (a)Original fundus image (b)Pre-
Processing image

2.3. To segment red lesions, the intensity information

of both green and red channels of the same fundus image is used for detecting the red lesions. To acauire this

histogram matching is used in which the histogram of the

green component of the image is modified with the

histogram of the red component of the same retinal

In order to do future research for existing systems need to improve and new solutions to the problem should be found out.

Table 1. Performance comparison of segmentation methods

References
[1] Dharitri Deka, Jyoti Prakash Medhi, S. R. Nirmala, ?Detection of macula and fovea for disease analysis in color fundus images,? in IEEE
2nd International Conference on Recent Trends in Information System,
2015

[2] T. Ruba, K. Ramalakshmi, ?Identification and Segmentation of exudates using SVM classifier,? IEEE Sponsored 2nd International
Conference on Innovation Embedded and Communication Systems, 2015

[3] Jyothis Jose, Jinsa Kuruvilla, ?Detection of red lesions and hard exudates in color fundus images,? Internation Journal of Engineering and
Computer Science ISSN:2319-7242 Volume 3 Issue 10 October, 2014 page No. 8583-8588

[4] JayakumarLachure, A. V. Deorankar, Sagar Lachure, Swati Gupta,
Romit Jadhav, ? Diabetic retinopathy using morphological operations and machine learning,? IEEE International Advance Computing Conference,
2015

[5] Sawmitra Kumar Kuri, ?automatic diabetic retinopathy detection using gabor filter with local entropy thresholding,? IEEE 2nd