An XNet-CNN Diabetic Retinal Image Classification Method

In this research,a retina image automatic recognition system based on Convolutional Neural Network (CNN) is proposed for the disadvantages of the traditional retina image processing process which is cumbersome and poor in robustness. First, image preprocessing includes noise removal, numerical norma...

Full description

Saved in:
Bibliographic Details
Main Authors: CHEN Yu, ZHOU Yujia, DING Hui
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2020-02-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1823
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399191075291136
author CHEN Yu
ZHOU Yujia
DING Hui
author_facet CHEN Yu
ZHOU Yujia
DING Hui
author_sort CHEN Yu
collection DOAJ
description In this research,a retina image automatic recognition system based on Convolutional Neural Network (CNN) is proposed for the disadvantages of the traditional retina image processing process which is cumbersome and poor in robustness. First, image preprocessing includes noise removal, numerical normalization, and data volume amplification; then, a new neural network model, XNet, is designed. XNet inherits the advantages of LeNet and Inception networks. The network parameters are based on training. The samples were adjusted adaptively. Finally, the comparison of accuracy and number of iterations was performed for different network structures. The experimental results show that the XNet network structure is superior to LeNet and Inception, and the accuracy rate can reach 91%; and the necessity of data amplification is confirmed through experiments.
format Article
id doaj-art-0e65f798cf5048cf9bb0341463374784
institution Kabale University
issn 1007-2683
language zho
publishDate 2020-02-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-0e65f798cf5048cf9bb03414633747842025-08-20T03:38:24ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832020-02-012501737910.15938/j.jhust.2020.01.011An XNet-CNN Diabetic Retinal Image Classification MethodCHEN Yu0ZHOU Yujia1DING Hui2School of Information and Computer Engineering of Northeast Forestry University, Harbin 150040, ChinaSchool of Information and Computer Engineering of Northeast Forestry University, Harbin 150040, ChinaHainan Eye Hospital, Haikou 570100, ChinaIn this research,a retina image automatic recognition system based on Convolutional Neural Network (CNN) is proposed for the disadvantages of the traditional retina image processing process which is cumbersome and poor in robustness. First, image preprocessing includes noise removal, numerical normalization, and data volume amplification; then, a new neural network model, XNet, is designed. XNet inherits the advantages of LeNet and Inception networks. The network parameters are based on training. The samples were adjusted adaptively. Finally, the comparison of accuracy and number of iterations was performed for different network structures. The experimental results show that the XNet network structure is superior to LeNet and Inception, and the accuracy rate can reach 91%; and the necessity of data amplification is confirmed through experiments.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1823convolution neural networkdeep learningretinal images classificationdiabetic retinal images
spellingShingle CHEN Yu
ZHOU Yujia
DING Hui
An XNet-CNN Diabetic Retinal Image Classification Method
Journal of Harbin University of Science and Technology
convolution neural network
deep learning
retinal images classification
diabetic retinal images
title An XNet-CNN Diabetic Retinal Image Classification Method
title_full An XNet-CNN Diabetic Retinal Image Classification Method
title_fullStr An XNet-CNN Diabetic Retinal Image Classification Method
title_full_unstemmed An XNet-CNN Diabetic Retinal Image Classification Method
title_short An XNet-CNN Diabetic Retinal Image Classification Method
title_sort xnet cnn diabetic retinal image classification method
topic convolution neural network
deep learning
retinal images classification
diabetic retinal images
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1823
work_keys_str_mv AT chenyu anxnetcnndiabeticretinalimageclassificationmethod
AT zhouyujia anxnetcnndiabeticretinalimageclassificationmethod
AT dinghui anxnetcnndiabeticretinalimageclassificationmethod
AT chenyu xnetcnndiabeticretinalimageclassificationmethod
AT zhouyujia xnetcnndiabeticretinalimageclassificationmethod
AT dinghui xnetcnndiabeticretinalimageclassificationmethod