INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Diabetic retinopathy could be a leading reason behind sightlessness among working-age adults. Early detection of this condition is crucial for a decent prognosis. during this paper, we tend to demonstrate the utilization of convolutional neural networks (CNNs) on color structure pictures for the popularity task of diabetic retinopathy staging. Our network models achieved check metric performance cherish baseline literature results, with a validation sensitivity of ninety fifth. Transfer learning on pre-trained GoogLeNet and AlexNet models from ImageNet improved peak check set accuracies to seventy four.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, severally.
"Diabetic Blindness Detection System using Convolution Neural Network", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.6, Issue 1, page no.53 - 60, January-2021, Available :http://www.ijsdr.org/papers/IJSDR2101008.pdf
Downloads:
000337212
Publication Details:
Published Paper ID: IJSDR2101008
Registration ID:192821
Published In: Volume 6 Issue 1, January-2021
DOI (Digital Object Identifier):
Page No: 53 - 60
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn