(18.205.26.39)
[ij] [ij] [ij] 
Email id
 

Research Journal of Pharmacy and Technology
Year : 2019, Volume : 12, Issue : 1
First page : ( 57) Last page : ( 61)
Print ISSN : 0974-3618. Online ISSN : 0974-360X.
Article DOI : 10.5958/0974-360X.2019.00011.8

Detecting Diabetic Retinopathy exudates in digital image processing Hybrid Methodology

Iyapparaja M.1,*, Sivakumar P.2

1Associate Professor, School of Information Technology and Engineering, VIT University, Vellore, Tamilnadu, India

2Associate Professor, CSE Department, Saudi Electronic University, Saudi Arabiya, Riyadh, Chennai, Tamil Nadu, India

*Corresponding Author E-mail: iyapparaja85@gmail.com

Online published on 16 March, 2019.

Abstract

Diabetic retinopathy (DR) is a serious eye infection which cause visual impairment. Henceforth, early discovery of DR is an absolute necessity. Exudates is the essential indication of Diabetics in retina. At the initial treatment of DR is conceivable in the event that we recognize Exudates at the most punctual arrange. The principle centralization of paper is to speak about strategies for productive discovery of Exudates. The first technique talks about Exudate discovery utilizing numerical morphology. The next procedure, proposes a half approach for detection of Exudates. These approach comprises of some phases pre-processing technique, grouping, and post processing. At the pre-processing stage, resizing the picture and morphological enlargement done. At grouping stage Linde Buzo-Grey is applied, k-implied calculation to recognize Exudates. In post preparing step, we expel every undesirable component segments in the picture to receive exact outcomes. The ideal outcomes will be got when the quantity of groups took is 8 in both of the grouping calculations.

Top

Keywords

Exudates, morphology, optic disk.

Top

  
║ Site map ║ Privacy Policy ║ Copyright ║ Terms & Conditions ║ Page Rank Tool
690,202,601 visitor(s) since 30th May, 2005.
All rights reserved. Site designed and maintained by DIVA ENTERPRISES PVT. LTD..
Note: Please use Internet Explorer (6.0 or above). Some functionalities may not work in other browsers.