Decision Tree Fusion and Improved Fundus Image Classification Algorithm

被引：0

作者：

Wang, Xiaofang ^{[1
]}

Qiu, Yanhua ^{[2
]}

Chen, Xin ^{[2
]}

Wu, Jialing ^{[2
]}

Zou, Qianying ^{[1
]}

Mu, Nan ^{[3
]}

机构：

[1] Geely Univ China, Chengdu 641423, Sichuan, Peoples R China

[2] Chengdu Coll Univ Elect Sci & Technol China, Chengdu 611731, Sichuan, Peoples R China

[3] Sichuan Normal Univ, Chengdu 610066, Sichuan, Peoples R China

来源：

GREEN, PERVASIVE, AND CLOUD COMPUTING, GPC 2022 | 2023年 / 13744卷

关键词：

Image classification; Butterworth parameter function; Improved UNet plus; Residual attention mechanism; Decision tree;

D O I：

10.1007/978-3-031-26118-3_3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In order to improve the effect of glaucoma fundus image classification, a new algorithm based on decision tree and UNet++ was proposed. Firstly, the image is divided into three channels of RGB, and the extracted green channel image is enhanced with the Butterworth parameter function of the fusion power function. Then the improved UNet++ network model is used to extract the texture features of the fundus image, and the residual module is used to enhance the texture features. The results of the experiment show that the average accuracy, the average specificity and the average sensitivity of the improved algorithm increase by 9.2%, 6.4% and 6.5% respectively. The improved algorithm is effective in glaucoma fundus image classification.

引用

页码：35 / 49

页数：15

共 19 条

[1] Aich G., 2021, 2021 INT C SMART GEN, P1
[2] An undrained expansion solution of cylindrical cavity in SANICLAY for K0-consolidated clays
Chen, Haohua
Mo, Pin-Qiang
[J]. JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING, 2022, 14 (03) : 922 - 935
[3] Chen X., 2020, J MIANYANG NORM U, V39, P25, DOI [10.16276/j.cnki.cn51-1670/g.2020.02.006, DOI 10.16276/J.CNKI.CN51-1670/G.2020.02.006]
[4] Diagnosis of glaucoma using CDR and NRR area in retina images
Das P.
Nirmala S.R.
Medhi J.P.
[J]. Das, Pranjal (pranjald255@gmail.com), 2016, Springer Verlag (05)
[5] Importance of Data Augmentation and Transfer Learning on Retinal Vessel Segmentation
Deari, Sabri
Oksuz, Ilkay
Ulukaya, Sezer
[J]. 2021 29TH TELECOMMUNICATIONS FORUM (TELFOR), 2021,
[6] Fang C, 2019, MICROELECTRON COMPUT, V36, P77, DOI [10.19304/j.cnki.issn1000-7180.2019.08.017, DOI 10.19304/J.CNKI.ISSN1000-7180.2019.08.017]
[7] Fu Y., 2021, MINICOMPUT SYST, V42, P1479
[8] Guo C., 2021, J COMPUT AIDED DESIG, V33, P363
[9] Local characterization of neovascularization and identification of proliferative diabetic retinopathy in retinal fundus images
Gupta, Garima
Kulasekaran, S.
Ram, Keerthi
Joshi, Niranjan
Sivaprakasam, Mohanasankar
Gandhi, Rashmin
[J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2017, 55 : 124 - 132
[10] Hao M, 2020, RES UNDERWATER IMAGE, DOI [10.26989/D.CNKI.GDLHU.2020.000020, DOI 10.26989/D.CNKI.GDLHU.2020.000020]

← 1 2 →