Identification of Armyworm-Infected Leaves in Corn by Image Processing and Deep Learning

IF 1.3 Q2 AGRICULTURE, MULTIDISCIPLINARY

Acta Technologica Agriculturae Pub Date : 2024-06-01 DOI:10.2478/ata-2024-0013

Nadia Saadati, R. Pourdarbani, S. Sabzi, José Luis Hernandez-Hernandez

{"title":"Identification of Armyworm-Infected Leaves in Corn by Image Processing and Deep Learning","authors":"Nadia Saadati, R. Pourdarbani, S. Sabzi, José Luis Hernandez-Hernandez","doi":"10.2478/ata-2024-0013","DOIUrl":null,"url":null,"abstract":"Abstract Corn is rich in fibre, vitamins, and minerals, and it is a nutritious source of carbohydrates. The area under corn cultivation is very large because, in addition to providing food for humans and animals, it is also used for raw materials for industrial products. Corn cultivation is exposed to the damage of various pests such as armyworm. A regional monitoring of pests is intended to actively track the population of this pest in a specific geography; one of the ways of monitoring is using the image processing technology. Therefore, the aim of this research was to identify healthy and armyworm-infected leaves using image processing and deep neural network in the form of 4 structures named AlexNet, DenseNet, EfficientNet, and GoogleNet. A total of 4500 images, including healthy and infected leaves, were collected. Next, models were trained by train data. Then, test data were evaluated using the evaluation criteria such as accuracy, precision, and F score. Results indicated all the classifiers obtained the precision above 98%, but the EfficientNet-based classifier was more successful in classification with the precision of 100%, accuracy of 99.70%, and F-score of 99.68%.","PeriodicalId":43089,"journal":{"name":"Acta Technologica Agriculturae","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Technologica Agriculturae","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2478/ata-2024-0013","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Abstract Corn is rich in fibre, vitamins, and minerals, and it is a nutritious source of carbohydrates. The area under corn cultivation is very large because, in addition to providing food for humans and animals, it is also used for raw materials for industrial products. Corn cultivation is exposed to the damage of various pests such as armyworm. A regional monitoring of pests is intended to actively track the population of this pest in a specific geography; one of the ways of monitoring is using the image processing technology. Therefore, the aim of this research was to identify healthy and armyworm-infected leaves using image processing and deep neural network in the form of 4 structures named AlexNet, DenseNet, EfficientNet, and GoogleNet. A total of 4500 images, including healthy and infected leaves, were collected. Next, models were trained by train data. Then, test data were evaluated using the evaluation criteria such as accuracy, precision, and F score. Results indicated all the classifiers obtained the precision above 98%, but the EfficientNet-based classifier was more successful in classification with the precision of 100%, accuracy of 99.70%, and F-score of 99.68%.

查看原文本刊更多论文

通过图像处理和深度学习识别玉米中受棉铃虫感染的叶片

摘要玉米富含纤维、维生素和矿物质，是碳水化合物的营养来源。玉米种植面积非常大，因为玉米除了为人类和动物提供食物外，还可用作工业产品的原材料。玉米种植会受到各种害虫的危害，如玉米螟。对害虫进行区域监测的目的是积极跟踪这种害虫在特定地域的数量；其中一种监测方法是使用图像处理技术。因此，本研究的目的是利用图像处理和深度神经网络（4 种结构，分别名为 AlexNet、DenseNet、EfficientNet 和 GoogleNet）来识别健康叶片和受红铃虫感染的叶片。研究共收集了 4500 张图像，其中包括健康叶片和受感染叶片。然后，通过训练数据对模型进行训练。然后，使用准确率、精确度和 F 分数等评估标准对测试数据进行评估。结果表明，所有分类器的精确度都在 98% 以上，但基于 EfficientNet 的分类器分类更成功，精确度为 100%，准确度为 99.70%，F 分数为 99.68%。

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

Acta Technologica Agriculturae AGRICULTURE, MULTIDISCIPLINARY-

CiteScore

2.50

自引率

28.60%

发文量

审稿时长

18 weeks

期刊介绍： Acta Technologica Agriculturae is an international scientific double-blind peer reviewed journal focused on agricultural engineering. The journal is multidisciplinary and publishes original research and review papers in engineering, agricultural and biological sciences, and materials science. Aims and Scope Areas of interest include but are not limited to: agricultural and biosystems engineering; machines and mechanization of agricultural production; information and electrical technologies; agro-product and food processing engineering; physical, chemical and biological changes in the soil caused by tillage and field traffic, soil working machinery and terramechanics; renewable energy sources and bioenergy; rural buildings; related issues from applied physics and chemistry, ecology, economy and energy.