Convolutional Neural Network Method for Effective Plant Disease Prediction

R. Mishra, Dhiraj Singh
{"title":"Convolutional Neural Network Method for Effective Plant Disease Prediction","authors":"R. Mishra, Dhiraj Singh","doi":"10.1109/ICICACS57338.2023.10099559","DOIUrl":null,"url":null,"abstract":"Agriculture as a source of food is essential for humankind. Therefore, the diagnosis of plant diseases is a significant concern. Plant disease diagnosis through plant monitoring is necessary for maintainable agriculture. Observing plant diseases automatically is very challenging. Managing plant diseases requires a lot of effort and expertise. Traditionally, identifying plant foliar disease is subjective, inefficient, and expensive, requiring a large number of personnel and a large amount of information about plant disease. This novel uses a deep learning-based Convolutional Neural Network (CNN) approach for plant disease identification to tackle this problem. First, collect the dataset from online Kaggle and pre-process images to remove noise in the first phase. Then Logistic Decision Regression (LDR) method was utilized for feature selection in the pre-processed plant image. After that, we apply segmentation based on selected features. Finally, our proposed method proficiently classifies the plant's disease based on segment images. Therefore, this approach produces high disease detection accuracy and specificity with a minimum error rate compared to different methods.","PeriodicalId":274807,"journal":{"name":"2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICACS57338.2023.10099559","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Agriculture as a source of food is essential for humankind. Therefore, the diagnosis of plant diseases is a significant concern. Plant disease diagnosis through plant monitoring is necessary for maintainable agriculture. Observing plant diseases automatically is very challenging. Managing plant diseases requires a lot of effort and expertise. Traditionally, identifying plant foliar disease is subjective, inefficient, and expensive, requiring a large number of personnel and a large amount of information about plant disease. This novel uses a deep learning-based Convolutional Neural Network (CNN) approach for plant disease identification to tackle this problem. First, collect the dataset from online Kaggle and pre-process images to remove noise in the first phase. Then Logistic Decision Regression (LDR) method was utilized for feature selection in the pre-processed plant image. After that, we apply segmentation based on selected features. Finally, our proposed method proficiently classifies the plant's disease based on segment images. Therefore, this approach produces high disease detection accuracy and specificity with a minimum error rate compared to different methods.
植物病害有效预测的卷积神经网络方法
农业作为食物来源对人类至关重要。因此,植物病害的诊断是一个重要的问题。通过植物监测诊断植物病害是可持续农业的必要手段。自动观察植物病害是非常有挑战性的。管理植物病害需要大量的努力和专业知识。传统上,植物叶面病害的识别是主观的、低效的、昂贵的,需要大量的人员和大量的植物病害信息。本小说使用基于深度学习的卷积神经网络(CNN)方法进行植物病害识别来解决这个问题。首先,从在线Kaggle中收集数据集,并在第一阶段对图像进行预处理,去除噪声。然后利用Logistic决策回归(LDR)方法对预处理后的植物图像进行特征选择。然后,我们根据选择的特征进行分割。最后,我们提出的方法基于片段图像对植物病害进行了熟练的分类。因此,与其他方法相比,该方法具有较高的疾病检测准确率和特异性,错误率最小。
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
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:604180095
Book学术官方微信