Performance Analysis of Deep Transfer Learning Models for the Automated Detection of Cotton Plant Diseases

IF 1.5 0 ENGINEERING, MULTIDISCIPLINARY
Sohail Anwar, Shoaib Rehman Soomro, Shadi Khan Baloch, Aamir Ali Patoli, Abdul Rahim Kolachi
{"title":"Performance Analysis of Deep Transfer Learning Models for the Automated Detection of Cotton Plant Diseases","authors":"Sohail Anwar, Shoaib Rehman Soomro, Shadi Khan Baloch, Aamir Ali Patoli, Abdul Rahim Kolachi","doi":"10.48084/etasr.6187","DOIUrl":null,"url":null,"abstract":"Cotton is one of the most important agricultural products and is closely linked to the economic development of Pakistan. However, the cotton plant is susceptible to bacterial and viral diseases that can quickly spread and damage plants and ultimately affect the cotton yield. The automated and early detection of affected plants can significantly reduce the potential spread of the disease. This paper presents the implementation and performance analysis of bacterial blight and curl virus disease detection in cotton crops through deep learning techniques. The automated disease detection is performed through transfer learning of six pre-trained deep learning models, namely DenseNet121, DenseNet169, MobileNetV2, ResNet50V2, VGG16, and VGG19. A total of 1362 images of local agricultural fields and 1292 images from online resources were used to train and validate the models. Image augmentation techniques were performed to increase the dataset diversity and size. Transfer learning was implemented for different image resolutions ranging from 32×32 to 256×256 pixels. Performance metrics such as accuracy, precision, recall, F1 Score, and prediction time were evaluated for each implemented model. The results indicate higher accuracy, up to 96%, for DenseNet169 and ResNet50V2 models when trained on the 256×256 pixels image dataset. The lowest accuracy, 52%, was obtained by the MobileNetV2 model when trained on low-resolution, 32×32, images. The confusion matrix analysis indicates the true-positive prediction rates higher than 91% for fresh leaves, 87% for bacterial blight, and 76% for curl virus detection for all implemented models when trained and tested on an image dataset of 128×128 pixels or higher resolution.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering, Technology & Applied Science Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48084/etasr.6187","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Cotton is one of the most important agricultural products and is closely linked to the economic development of Pakistan. However, the cotton plant is susceptible to bacterial and viral diseases that can quickly spread and damage plants and ultimately affect the cotton yield. The automated and early detection of affected plants can significantly reduce the potential spread of the disease. This paper presents the implementation and performance analysis of bacterial blight and curl virus disease detection in cotton crops through deep learning techniques. The automated disease detection is performed through transfer learning of six pre-trained deep learning models, namely DenseNet121, DenseNet169, MobileNetV2, ResNet50V2, VGG16, and VGG19. A total of 1362 images of local agricultural fields and 1292 images from online resources were used to train and validate the models. Image augmentation techniques were performed to increase the dataset diversity and size. Transfer learning was implemented for different image resolutions ranging from 32×32 to 256×256 pixels. Performance metrics such as accuracy, precision, recall, F1 Score, and prediction time were evaluated for each implemented model. The results indicate higher accuracy, up to 96%, for DenseNet169 and ResNet50V2 models when trained on the 256×256 pixels image dataset. The lowest accuracy, 52%, was obtained by the MobileNetV2 model when trained on low-resolution, 32×32, images. The confusion matrix analysis indicates the true-positive prediction rates higher than 91% for fresh leaves, 87% for bacterial blight, and 76% for curl virus detection for all implemented models when trained and tested on an image dataset of 128×128 pixels or higher resolution.
深度迁移学习模型在棉花病害自动检测中的性能分析
棉花是巴基斯坦最重要的农产品之一,与巴基斯坦的经济发展息息相关。然而,棉花容易受到细菌和病毒疾病的影响,这些疾病可以迅速传播并损害植株,最终影响棉花产量。受影响植物的自动化和早期检测可以显着减少疾病的潜在传播。本文介绍了利用深度学习技术对棉花白叶枯病和卷曲病毒病害进行检测的实现和性能分析。通过对DenseNet121、DenseNet169、MobileNetV2、ResNet50V2、VGG16和VGG19这6个预训练深度学习模型进行迁移学习,实现疾病自动检测。利用1362张当地农田图像和1292张在线资源图像对模型进行训练和验证。采用图像增强技术来增加数据集的多样性和大小。迁移学习实现了不同的图像分辨率范围从32×32到256×256像素。对每个实现的模型评估了准确性、精密度、召回率、F1 Score和预测时间等性能指标。结果表明,当在256×256像素图像数据集上训练时,DenseNet169和ResNet50V2模型的准确率高达96%。在低分辨率(32×32)图像上训练时,MobileNetV2模型的准确率最低,为52%。混淆矩阵分析表明,当在128×128像素或更高分辨率的图像数据集上进行训练和测试时,所有实现模型的真阳性预测率高于新鲜叶片的91%,细菌枯萎病的87%和卷曲病毒检测的76%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Engineering, Technology & Applied Science Research
Engineering, Technology & Applied Science Research ENGINEERING, MULTIDISCIPLINARY-
CiteScore
3.00
自引率
46.70%
发文量
222
审稿时长
11 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信