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

Retinal Disorder Detection Using Image Processing and Machine Learning


Swaroop. M. G , PES College of Engineering; Dr. M. N. Veena, PES College of Engineering


Image Processing, Machine Learning


Diabetes happens when the pancreas neglects to emit enough insulin, gradually influencing the retina of the human eye, prompting diabetic retinopathy. The veins in the retina get adjusted and have variation from the norm. Exudates are discharged, miniaturized scale aneurysms and hemorrhages happen in the retina. The appearance of these highlights speaks to the level of seriousness of the illness. Early location of diabetic retinopathy plays a real job in the accomplishment of such infection treatment. The fundamental challenge is to separate exudates which are comparative in shading property and size of the optic plate, and after that small scale aneurysms are comparable in shading and vicinity with veins. The primary goal of the paper is to build up a PC helped recognition framework to discover the variation from the norm of retinal imaging and recognizes the nearness of irregularity highlights from retinal fundus pictures. There is not many existing examination works have been experienced by applying AI procedures, however existing methodologies have not accomplished a decent precision of identification and they have not yielded effective execution in diverse datasets. The proposed technique is to upgrade the picture and channel the clamor, distinguish vein and recognize the optic circle, remove the exudates and miniaturized scale aneurysms, separate the highlights and characterize various phases of diabetic retinopathy into gentle, moderate, extreme non-proliferative diabetic retinopathy (NPDR) and proliferative Diabetic retinopathy (PDR) by utilizing proposed AI strategies. The expected yield of proposed work in this paper will be a starter structure and pilot model advancement.

Other Details

Paper ID: IJSRDV7I31152
Published in: Volume : 7, Issue : 3
Publication Date: 01/06/2019
Page(s): 1731-1734

Article Preview

Download Article