No Cover Image

Journal article 58 views 3 downloads

An efficient convolutional neural network-based diagnosis system for citrus fruit diseases

Zhangcai Huang, Xiaoxiao Jiang, Shaodong Huang, Sheng Qin, Scott Yang Orcid Logo

Frontiers in Genetics, Volume: 14

Swansea University Author: Scott Yang Orcid Logo

  • 66057.pdf

    PDF | Version of Record

    © 2023 Huang, Jiang, Huang, Qin and Yang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).

    Download (2.31MB)

Check full text

DOI (Published version): 10.3389/fgene.2023.1253934

Abstract

Introduction: Fruit diseases have a serious impact on fruit production, causing a significant drop in economic returns from agricultural products. Due to its excellent performance, deep learning is widely used for disease identification and severity diagnosis of crops. This paper focuses on leveragi...

Full description

Published in: Frontiers in Genetics
ISSN: 1664-8021
Published: Frontiers Media SA 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa66057
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-04-15T13:18:07Z
last_indexed 2024-04-15T13:18:07Z
id cronfa66057
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>66057</id><entry>2024-04-15</entry><title>An efficient convolutional neural network-based diagnosis system for citrus fruit diseases</title><swanseaauthors><author><sid>81dc663ca0e68c60908d35b1d2ec3a9b</sid><ORCID>0000-0002-6618-7483</ORCID><firstname>Scott</firstname><surname>Yang</surname><name>Scott Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-04-15</date><deptcode>MACS</deptcode><abstract>Introduction: Fruit diseases have a serious impact on fruit production, causing a significant drop in economic returns from agricultural products. Due to its excellent performance, deep learning is widely used for disease identification and severity diagnosis of crops. This paper focuses on leveraging the high-latitude feature extraction capability of deep convolutional neural networks to improve classification performance.Methods: The proposed neural network is formed by combining the Inception module with the current state-of-the-art EfficientNetV2 for better multi-scale feature extraction and disease identification of citrus fruits. The VGG is used to replace the U-Net backbone to enhance the segmentation performance of the network.Results: Compared to existing networks, the proposed method achieved recognition accuracy of over 95%. In addition, the accuracies of the segmentation models were compared. VGG-U-Net, a network generated by replacing the backbone of U-Net with VGG, is found to have the best segmentation performance with an accuracy of 87.66%. This method is most suitable for diagnosing the severity level of citrus fruit diseases. In the meantime, transfer learning is applied to improve the training cycle of the network model, both in the detection and severity diagnosis phases of the disease.Discussion: The results of the comparison experiments reveal that the proposed method is effective in identifying and diagnosing the severity of citrus fruit diseases identification.</abstract><type>Journal Article</type><journal>Frontiers in Genetics</journal><volume>14</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Frontiers Media SA</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1664-8021</issnElectronic><keywords>identification and quantification, high-latitude features, EfficientNetv2, VGG, U-net</keywords><publishedDay>24</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-08-24</publishedDate><doi>10.3389/fgene.2023.1253934</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This research is supported by the Guangxi Natural Science Foundation under Grant 022GXNSFFA035028, research fund of Guangxi Normal University under Grant 2021JC006, the AI + Education research project of Guangxi Humanities Society Science Development Research Center under Grant ZXZJ202205.</funders><projectreference/><lastEdited>2024-05-22T12:12:11.0664080</lastEdited><Created>2024-04-15T11:15:52.8196220</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Zhangcai</firstname><surname>Huang</surname><order>1</order></author><author><firstname>Xiaoxiao</firstname><surname>Jiang</surname><order>2</order></author><author><firstname>Shaodong</firstname><surname>Huang</surname><order>3</order></author><author><firstname>Sheng</firstname><surname>Qin</surname><order>4</order></author><author><firstname>Scott</firstname><surname>Yang</surname><orcid>0000-0002-6618-7483</orcid><order>5</order></author></authors><documents><document><filename>66057__30018__48b3c715b779479bb6cb122eae783312.pdf</filename><originalFilename>66057.pdf</originalFilename><uploaded>2024-04-15T14:18:06.1463525</uploaded><type>Output</type><contentLength>2419796</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 Huang, Jiang, Huang, Qin and Yang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 66057 2024-04-15 An efficient convolutional neural network-based diagnosis system for citrus fruit diseases 81dc663ca0e68c60908d35b1d2ec3a9b 0000-0002-6618-7483 Scott Yang Scott Yang true false 2024-04-15 MACS Introduction: Fruit diseases have a serious impact on fruit production, causing a significant drop in economic returns from agricultural products. Due to its excellent performance, deep learning is widely used for disease identification and severity diagnosis of crops. This paper focuses on leveraging the high-latitude feature extraction capability of deep convolutional neural networks to improve classification performance.Methods: The proposed neural network is formed by combining the Inception module with the current state-of-the-art EfficientNetV2 for better multi-scale feature extraction and disease identification of citrus fruits. The VGG is used to replace the U-Net backbone to enhance the segmentation performance of the network.Results: Compared to existing networks, the proposed method achieved recognition accuracy of over 95%. In addition, the accuracies of the segmentation models were compared. VGG-U-Net, a network generated by replacing the backbone of U-Net with VGG, is found to have the best segmentation performance with an accuracy of 87.66%. This method is most suitable for diagnosing the severity level of citrus fruit diseases. In the meantime, transfer learning is applied to improve the training cycle of the network model, both in the detection and severity diagnosis phases of the disease.Discussion: The results of the comparison experiments reveal that the proposed method is effective in identifying and diagnosing the severity of citrus fruit diseases identification. Journal Article Frontiers in Genetics 14 Frontiers Media SA 1664-8021 identification and quantification, high-latitude features, EfficientNetv2, VGG, U-net 24 8 2023 2023-08-24 10.3389/fgene.2023.1253934 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Another institution paid the OA fee This research is supported by the Guangxi Natural Science Foundation under Grant 022GXNSFFA035028, research fund of Guangxi Normal University under Grant 2021JC006, the AI + Education research project of Guangxi Humanities Society Science Development Research Center under Grant ZXZJ202205. 2024-05-22T12:12:11.0664080 2024-04-15T11:15:52.8196220 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zhangcai Huang 1 Xiaoxiao Jiang 2 Shaodong Huang 3 Sheng Qin 4 Scott Yang 0000-0002-6618-7483 5 66057__30018__48b3c715b779479bb6cb122eae783312.pdf 66057.pdf 2024-04-15T14:18:06.1463525 Output 2419796 application/pdf Version of Record true © 2023 Huang, Jiang, Huang, Qin and Yang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). true eng https://creativecommons.org/licenses/by/4.0/
title An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
spellingShingle An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
Scott Yang
title_short An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
title_full An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
title_fullStr An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
title_full_unstemmed An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
title_sort An efficient convolutional neural network-based diagnosis system for citrus fruit diseases
author_id_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b
author_id_fullname_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b_***_Scott Yang
author Scott Yang
author2 Zhangcai Huang
Xiaoxiao Jiang
Shaodong Huang
Sheng Qin
Scott Yang
format Journal article
container_title Frontiers in Genetics
container_volume 14
publishDate 2023
institution Swansea University
issn 1664-8021
doi_str_mv 10.3389/fgene.2023.1253934
publisher Frontiers Media SA
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description Introduction: Fruit diseases have a serious impact on fruit production, causing a significant drop in economic returns from agricultural products. Due to its excellent performance, deep learning is widely used for disease identification and severity diagnosis of crops. This paper focuses on leveraging the high-latitude feature extraction capability of deep convolutional neural networks to improve classification performance.Methods: The proposed neural network is formed by combining the Inception module with the current state-of-the-art EfficientNetV2 for better multi-scale feature extraction and disease identification of citrus fruits. The VGG is used to replace the U-Net backbone to enhance the segmentation performance of the network.Results: Compared to existing networks, the proposed method achieved recognition accuracy of over 95%. In addition, the accuracies of the segmentation models were compared. VGG-U-Net, a network generated by replacing the backbone of U-Net with VGG, is found to have the best segmentation performance with an accuracy of 87.66%. This method is most suitable for diagnosing the severity level of citrus fruit diseases. In the meantime, transfer learning is applied to improve the training cycle of the network model, both in the detection and severity diagnosis phases of the disease.Discussion: The results of the comparison experiments reveal that the proposed method is effective in identifying and diagnosing the severity of citrus fruit diseases identification.
published_date 2023-08-24T12:12:10Z
_version_ 1799751026779095040
score 11.012924

Similar Items