害虫检测和识别:一种使用深度学习技术的方法

N. C. Kundur, P. Mallikarjuna
{"title":"害虫检测和识别:一种使用深度学习技术的方法","authors":"N. C. Kundur, P. Mallikarjuna","doi":"10.1109/CCIP57447.2022.10058692","DOIUrl":null,"url":null,"abstract":"Insect pest management is one of the most important ways to enhance crop productivity and quality in agriculture. We need to detect insect pest's timely and accurate manner, which is critical to agricultural production. This paper aims to provide effective pest detection in a wide area. The real-time application of this work can be used to detect pest which affects agricultural crops vastly. Here deep learning algorithm is used to detect pests for an IP102 dataset which consists of 75000 images. We have implemented the K-Means clustering algorithm which is used for creating groups of classes or clusters for pixel-based extraction of pests using Mat lab. Performance metrics like algorithm accuracy, precision, recall, and F-1 score are evaluated accordingly. We have obtained a validation accuracy of 97.98% which outperforms the other existing methods.","PeriodicalId":309964,"journal":{"name":"2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pest Detection and Recognition: An approach using Deep Learning Techniques\",\"authors\":\"N. C. Kundur, P. Mallikarjuna\",\"doi\":\"10.1109/CCIP57447.2022.10058692\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Insect pest management is one of the most important ways to enhance crop productivity and quality in agriculture. We need to detect insect pest's timely and accurate manner, which is critical to agricultural production. This paper aims to provide effective pest detection in a wide area. The real-time application of this work can be used to detect pest which affects agricultural crops vastly. Here deep learning algorithm is used to detect pests for an IP102 dataset which consists of 75000 images. We have implemented the K-Means clustering algorithm which is used for creating groups of classes or clusters for pixel-based extraction of pests using Mat lab. Performance metrics like algorithm accuracy, precision, recall, and F-1 score are evaluated accordingly. We have obtained a validation accuracy of 97.98% which outperforms the other existing methods.\",\"PeriodicalId\":309964,\"journal\":{\"name\":\"2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCIP57447.2022.10058692\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCIP57447.2022.10058692","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

病虫害治理是提高农业作物生产力和质量的重要途径之一。我们需要及时、准确地检测害虫,这对农业生产至关重要。本文的目的是在广泛的范围内提供有效的害虫检测。该技术的实时应用可用于对农作物危害较大的有害生物的检测。本文使用深度学习算法对IP102数据集进行害虫检测,该数据集包含75000张图像。我们已经实现了K-Means聚类算法,该算法用于创建类组或聚类,用于使用Mat lab基于像素的害虫提取。性能指标,如算法的准确性,精度,召回率和F-1分数进行相应的评估。验证精度为97.98%,优于现有的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Pest Detection and Recognition: An approach using Deep Learning Techniques
Insect pest management is one of the most important ways to enhance crop productivity and quality in agriculture. We need to detect insect pest's timely and accurate manner, which is critical to agricultural production. This paper aims to provide effective pest detection in a wide area. The real-time application of this work can be used to detect pest which affects agricultural crops vastly. Here deep learning algorithm is used to detect pests for an IP102 dataset which consists of 75000 images. We have implemented the K-Means clustering algorithm which is used for creating groups of classes or clusters for pixel-based extraction of pests using Mat lab. Performance metrics like algorithm accuracy, precision, recall, and F-1 score are evaluated accordingly. We have obtained a validation accuracy of 97.98% which outperforms the other existing methods.
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
自引率
0.00%
发文量
0
×
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