利用深度神经网络识别大麦病害

IF 4.5 1区 农林科学 Q1 AGRONOMY European Journal of Agronomy Pub Date : 2024-09-13 DOI:10.1016/j.eja.2024.127359
Masoud Rezaei , Sanjiv Gupta , Dean Diepeveen , Hamid Laga , Michael G.K. Jones , Ferdous Sohel
{"title":"利用深度神经网络识别大麦病害","authors":"Masoud Rezaei ,&nbsp;Sanjiv Gupta ,&nbsp;Dean Diepeveen ,&nbsp;Hamid Laga ,&nbsp;Michael G.K. Jones ,&nbsp;Ferdous Sohel","doi":"10.1016/j.eja.2024.127359","DOIUrl":null,"url":null,"abstract":"<div><p>Plant disease negatively impacts food production and quality. It is crucial to detect and recognise plant diseases correctly. Traditional approaches do not offer a rapid and comprehensive management system for detecting plant diseases. Deep learning techniques (DL) have achieved encouraging results in discriminating patterns and anomalies in visual samples. This ability provides an effective method to diagnose any plant disease symptoms automatically. However, one of the limitations of recent studies is that in-field disease detection is underexplored, so developing a model that performs well for in-field samples is necessary. The objective of this study is to develop and investigate DL techniques for in-field disease detection of barley (<em>Hordeum vulgare</em> L.), one of the main crops in Australia, given visual samples captured at barley trials using a consumer-grade RGB camera. Consequently, A dataset was captured from test-bed trials across multiple paddocks infected with three diseases: net form net blotch (NFNB), spot form net blotch (SFNB), and scald, in various weather conditions. The collected data, 312 images (6000 × 4000 pixels), are divided into patches of 448 × 448 pixels, which are manually annotated into four classes: no-disease, scald, NFNB and SFNB. Finally, the data was augmented using random rotation and flip to increase the dataset size. The generated barley disease dataset is then applied to several well-known pre-trained DL networks such as DenseNet, ResNet, InceptionV3, Xception, and MobileNet as the network backbone. Given limited data, these methods can be trained to detect anomalies in visual samples. The results show that MobileNet, Xception, and InceptionV3 performed well in barley disease detection. On the other hand, ResNet showed poor classification ability. Moreover, Augmenting the data improves the performance of DL networks, particularly for underperforming backbones like ResNet, and mitigates the limited data access for these data-intensive networks. The augmentation step improved MobileNet performance by approximately 6 %. MobileNet achieved the highest accuracy of 98.63 % (the average of the three diseases) in binary classification and an accuracy of 93.50 % in multi-class classification. Even though classifying SFNB and NFNB is challenging in the early stages, MobileNet achieved the minimum misclassification rate among the two diseases. The results show the efficiency of this model in diagnosing barley diseases using complex data collected from the field environment. In addition, the model is lighter and comprises fewer trainable parameters. Consequently, MobileNet is suitable for small training datasets, reducing data acquisition costs.</p></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127359"},"PeriodicalIF":4.5000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1161030124002806/pdfft?md5=2cec48c1977ddea1cd255fc4cdac2d15&pid=1-s2.0-S1161030124002806-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Barley disease recognition using deep neural networks\",\"authors\":\"Masoud Rezaei ,&nbsp;Sanjiv Gupta ,&nbsp;Dean Diepeveen ,&nbsp;Hamid Laga ,&nbsp;Michael G.K. Jones ,&nbsp;Ferdous Sohel\",\"doi\":\"10.1016/j.eja.2024.127359\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Plant disease negatively impacts food production and quality. It is crucial to detect and recognise plant diseases correctly. Traditional approaches do not offer a rapid and comprehensive management system for detecting plant diseases. Deep learning techniques (DL) have achieved encouraging results in discriminating patterns and anomalies in visual samples. This ability provides an effective method to diagnose any plant disease symptoms automatically. However, one of the limitations of recent studies is that in-field disease detection is underexplored, so developing a model that performs well for in-field samples is necessary. The objective of this study is to develop and investigate DL techniques for in-field disease detection of barley (<em>Hordeum vulgare</em> L.), one of the main crops in Australia, given visual samples captured at barley trials using a consumer-grade RGB camera. Consequently, A dataset was captured from test-bed trials across multiple paddocks infected with three diseases: net form net blotch (NFNB), spot form net blotch (SFNB), and scald, in various weather conditions. The collected data, 312 images (6000 × 4000 pixels), are divided into patches of 448 × 448 pixels, which are manually annotated into four classes: no-disease, scald, NFNB and SFNB. Finally, the data was augmented using random rotation and flip to increase the dataset size. The generated barley disease dataset is then applied to several well-known pre-trained DL networks such as DenseNet, ResNet, InceptionV3, Xception, and MobileNet as the network backbone. Given limited data, these methods can be trained to detect anomalies in visual samples. The results show that MobileNet, Xception, and InceptionV3 performed well in barley disease detection. On the other hand, ResNet showed poor classification ability. Moreover, Augmenting the data improves the performance of DL networks, particularly for underperforming backbones like ResNet, and mitigates the limited data access for these data-intensive networks. The augmentation step improved MobileNet performance by approximately 6 %. MobileNet achieved the highest accuracy of 98.63 % (the average of the three diseases) in binary classification and an accuracy of 93.50 % in multi-class classification. Even though classifying SFNB and NFNB is challenging in the early stages, MobileNet achieved the minimum misclassification rate among the two diseases. The results show the efficiency of this model in diagnosing barley diseases using complex data collected from the field environment. In addition, the model is lighter and comprises fewer trainable parameters. Consequently, MobileNet is suitable for small training datasets, reducing data acquisition costs.</p></div>\",\"PeriodicalId\":51045,\"journal\":{\"name\":\"European Journal of Agronomy\",\"volume\":\"161 \",\"pages\":\"Article 127359\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1161030124002806/pdfft?md5=2cec48c1977ddea1cd255fc4cdac2d15&pid=1-s2.0-S1161030124002806-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Agronomy\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1161030124002806\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Agronomy","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1161030124002806","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0

摘要

植物病害会对粮食生产和质量造成负面影响。正确检测和识别植物病害至关重要。传统方法无法提供快速、全面的植物病害检测管理系统。深度学习技术(DL)在辨别视觉样本中的模式和异常方面取得了令人鼓舞的成果。这种能力为自动诊断任何植物病害症状提供了有效方法。然而,近期研究的局限性之一是对田间病害检测的探索不足,因此有必要开发一种能很好地检测田间样本的模型。本研究的目的是利用消费级 RGB 相机在大麦试验中采集的视觉样本,开发和研究用于大麦(Hordeum vulgare L.)(澳大利亚主要农作物之一)田间病害检测的 DL 技术。因此,在不同的天气条件下,从感染了三种病害(网状网斑病(NFNB)、点状网斑病(SFNB)和烫伤)的多个围场的试验台试验中采集了数据集。收集到的 312 幅图像(6000 × 4000 像素)被划分为 448 × 448 像素的斑块,这些斑块被人工标注为四个等级:无病、烫伤、NFNB 和 SFNB。最后,使用随机旋转和翻转来增加数据集的大小。然后,将生成的大麦疾病数据集应用于几个著名的预训练 DL 网络,如 DenseNet、ResNet、InceptionV3、Xception 和 MobileNet 作为网络骨干。在数据有限的情况下,这些方法可以训练成检测视觉样本中的异常。结果表明,MobileNet、Xception 和 InceptionV3 在大麦病害检测中表现良好。另一方面,ResNet 的分类能力较差。此外,扩增数据提高了 DL 网络的性能,尤其是对于 ResNet 这样性能不佳的骨干网络,并缓解了这些数据密集型网络的数据访问受限问题。扩增步骤将 MobileNet 的性能提高了约 6%。MobileNet 的二元分类准确率最高,达到 98.63%(三种疾病的平均值),多类分类准确率为 93.50%。尽管在早期阶段对 SFNB 和 NFNB 进行分类具有挑战性,但在这两种疾病中,MobileNet 的误分类率最低。这些结果表明,该模型在使用从田间环境收集的复杂数据诊断大麦疾病时非常高效。此外,该模型重量更轻,可训练参数更少。因此,MobileNet 适用于小型训练数据集,从而降低了数据采集成本。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Barley disease recognition using deep neural networks

Plant disease negatively impacts food production and quality. It is crucial to detect and recognise plant diseases correctly. Traditional approaches do not offer a rapid and comprehensive management system for detecting plant diseases. Deep learning techniques (DL) have achieved encouraging results in discriminating patterns and anomalies in visual samples. This ability provides an effective method to diagnose any plant disease symptoms automatically. However, one of the limitations of recent studies is that in-field disease detection is underexplored, so developing a model that performs well for in-field samples is necessary. The objective of this study is to develop and investigate DL techniques for in-field disease detection of barley (Hordeum vulgare L.), one of the main crops in Australia, given visual samples captured at barley trials using a consumer-grade RGB camera. Consequently, A dataset was captured from test-bed trials across multiple paddocks infected with three diseases: net form net blotch (NFNB), spot form net blotch (SFNB), and scald, in various weather conditions. The collected data, 312 images (6000 × 4000 pixels), are divided into patches of 448 × 448 pixels, which are manually annotated into four classes: no-disease, scald, NFNB and SFNB. Finally, the data was augmented using random rotation and flip to increase the dataset size. The generated barley disease dataset is then applied to several well-known pre-trained DL networks such as DenseNet, ResNet, InceptionV3, Xception, and MobileNet as the network backbone. Given limited data, these methods can be trained to detect anomalies in visual samples. The results show that MobileNet, Xception, and InceptionV3 performed well in barley disease detection. On the other hand, ResNet showed poor classification ability. Moreover, Augmenting the data improves the performance of DL networks, particularly for underperforming backbones like ResNet, and mitigates the limited data access for these data-intensive networks. The augmentation step improved MobileNet performance by approximately 6 %. MobileNet achieved the highest accuracy of 98.63 % (the average of the three diseases) in binary classification and an accuracy of 93.50 % in multi-class classification. Even though classifying SFNB and NFNB is challenging in the early stages, MobileNet achieved the minimum misclassification rate among the two diseases. The results show the efficiency of this model in diagnosing barley diseases using complex data collected from the field environment. In addition, the model is lighter and comprises fewer trainable parameters. Consequently, MobileNet is suitable for small training datasets, reducing data acquisition costs.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
European Journal of Agronomy
European Journal of Agronomy 农林科学-农艺学
CiteScore
8.30
自引率
7.70%
发文量
187
审稿时长
4.5 months
期刊介绍: The European Journal of Agronomy, the official journal of the European Society for Agronomy, publishes original research papers reporting experimental and theoretical contributions to field-based agronomy and crop science. The journal will consider research at the field level for agricultural, horticultural and tree crops, that uses comprehensive and explanatory approaches. The EJA covers the following topics: crop physiology crop production and management including irrigation, fertilization and soil management agroclimatology and modelling plant-soil relationships crop quality and post-harvest physiology farming and cropping systems agroecosystems and the environment crop-weed interactions and management organic farming horticultural crops papers from the European Society for Agronomy bi-annual meetings In determining the suitability of submitted articles for publication, particular scrutiny is placed on the degree of novelty and significance of the research and the extent to which it adds to existing knowledge in agronomy.
期刊最新文献
Ex-ante analyses using machine learning to understand the interactive influences of environmental and agro-management variables for target-oriented management practice selection Organo-mineral fertilizer to sustain soil health and crop yield for reducing environmental impact: A comprehensive review Investigation of coupling DSSAT with SCOPE-RTMo via sensitivity analysis and use of this coupled crop-radiative transfer model for sensitivity-based data assimilation Long term analysis on Olive flowering and climatic relationships in central Italy Sustainable effects of nitrogen reduction combined with biochar on enhancing maize productivity and nitrogen utilization
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1