Citrus Disease Classification Model Based on Improved ConvNeXt

Early diagnosis of citrus diseases directly affects the yield and quality of citrus cultivation, and a citrus disease classification model based on improved ConvNeXt is proposed to address the problems of high cost and low efficiency of traditional citrus disease detection methods. Firstly, the atte...

Full description

Saved in:
Bibliographic Details
Main Authors: Jichi Yan, Yongbin Mo, Yannan Yu, Shiqing Dou, Rongfeng Yang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10565900/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850210378724671488
author Jichi Yan
Yongbin Mo
Yannan Yu
Shiqing Dou
Rongfeng Yang
author_facet Jichi Yan
Yongbin Mo
Yannan Yu
Shiqing Dou
Rongfeng Yang
author_sort Jichi Yan
collection DOAJ
description Early diagnosis of citrus diseases directly affects the yield and quality of citrus cultivation, and a citrus disease classification model based on improved ConvNeXt is proposed to address the problems of high cost and low efficiency of traditional citrus disease detection methods. Firstly, the attention mechanism is changed to a parallel connection in the convolutional block attention module, and the attention mechanism is incorporated into ConvNeXt, which improves the model’s ability of feature extraction, makes the model focus more on lesion features, and suppresses the interference of background information. Secondly, the multi-scale feature fusion module is incorporated to improve the model’s adaptability to disease features at different scales and improve the network classification performance. Finally, the transfer learning method is used to conduct pre-training with ImageNet weight information to reduce the impact of insufficient samples. The experimental results show that on the self-constructed complex background citrus disease dataset, the model in this paper achieves an average accuracy of 98.07%, which is improved by 2.9% compared with the original model, and the comprehensive performance is significantly better than that of VGG, AlexNet, and other models. The model in this paper improves the performance of disease classification and provides a theoretical basis for intelligent classification of citrus diseases.
format Article
id doaj-art-92dd5c333b5e412bb99090feac2d3740
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-92dd5c333b5e412bb99090feac2d37402025-08-20T02:09:47ZengIEEEIEEE Access2169-35362024-01-011215249815251010.1109/ACCESS.2024.341731010565900Citrus Disease Classification Model Based on Improved ConvNeXtJichi Yan0Yongbin Mo1https://orcid.org/0009-0001-5218-3246Yannan Yu2Shiqing Dou3Rongfeng Yang4Education Department of Guangxi Zhuang Autonomous Region, Key Laboratory of Advanced Manufacturing and Automation Technology, Guilin University of Technology, Guilin, ChinaSchool of Mechanical and Control Engineering, Guilin University of Technology, Guilin, ChinaEducation Department of Guangxi Zhuang Autonomous Region, Key Laboratory of Advanced Manufacturing and Automation Technology, Guilin University of Technology, Guilin, ChinaSchool of Surveying, Mapping and Geographic Information, Guilin University of Technology, Guilin, ChinaSchool of Marine Engineering, Jimei University, Xiamen, ChinaEarly diagnosis of citrus diseases directly affects the yield and quality of citrus cultivation, and a citrus disease classification model based on improved ConvNeXt is proposed to address the problems of high cost and low efficiency of traditional citrus disease detection methods. Firstly, the attention mechanism is changed to a parallel connection in the convolutional block attention module, and the attention mechanism is incorporated into ConvNeXt, which improves the model’s ability of feature extraction, makes the model focus more on lesion features, and suppresses the interference of background information. Secondly, the multi-scale feature fusion module is incorporated to improve the model’s adaptability to disease features at different scales and improve the network classification performance. Finally, the transfer learning method is used to conduct pre-training with ImageNet weight information to reduce the impact of insufficient samples. The experimental results show that on the self-constructed complex background citrus disease dataset, the model in this paper achieves an average accuracy of 98.07%, which is improved by 2.9% compared with the original model, and the comprehensive performance is significantly better than that of VGG, AlexNet, and other models. The model in this paper improves the performance of disease classification and provides a theoretical basis for intelligent classification of citrus diseases.https://ieeexplore.ieee.org/document/10565900/Citrus diseasedeep learningattention mechanismConvNeXt
spellingShingle Jichi Yan
Yongbin Mo
Yannan Yu
Shiqing Dou
Rongfeng Yang
Citrus Disease Classification Model Based on Improved ConvNeXt
IEEE Access
Citrus disease
deep learning
attention mechanism
ConvNeXt
title Citrus Disease Classification Model Based on Improved ConvNeXt
title_full Citrus Disease Classification Model Based on Improved ConvNeXt
title_fullStr Citrus Disease Classification Model Based on Improved ConvNeXt
title_full_unstemmed Citrus Disease Classification Model Based on Improved ConvNeXt
title_short Citrus Disease Classification Model Based on Improved ConvNeXt
title_sort citrus disease classification model based on improved convnext
topic Citrus disease
deep learning
attention mechanism
ConvNeXt
url https://ieeexplore.ieee.org/document/10565900/
work_keys_str_mv AT jichiyan citrusdiseaseclassificationmodelbasedonimprovedconvnext
AT yongbinmo citrusdiseaseclassificationmodelbasedonimprovedconvnext
AT yannanyu citrusdiseaseclassificationmodelbasedonimprovedconvnext
AT shiqingdou citrusdiseaseclassificationmodelbasedonimprovedconvnext
AT rongfengyang citrusdiseaseclassificationmodelbasedonimprovedconvnext