Texture features extraction technology using grey level co-occurrence matrix for the k-nearest neighbor classification of citrus disease: an agro-economic analysis

IF 0.6 Q2 Social Sciences Economic Annals-XXI Pub Date : 2022-06-22 DOI:10.21003/ea.v197-06
Wilis Kaswidjanti, Hidayatulah Himawan, Galih Wangi Putri
{"title":"Texture features extraction technology using grey level co-occurrence matrix for the k-nearest neighbor classification of citrus disease: an agro-economic analysis","authors":"Wilis Kaswidjanti, Hidayatulah Himawan, Galih Wangi Putri","doi":"10.21003/ea.v197-06","DOIUrl":null,"url":null,"abstract":"The citrus disease is a problem affecting the decrease of agricultural commodity yields. One way to determine disease in citrus is through the leaves. Leaves, as a place for photosynthesis, with the disease will cause stunted plant growth. This study revolves around an Agro-economic Analysis to classify citrus diseases based on leaf images by applying the Gray Level Co-occurrence Matrix (GLCM) extraction technology using K-Nearest Neighbor (KNN). To meet that aim, Otsu Thresholding segmentation is carried out to separate the disease’s image from the healthy leaves. This experiment was carried out in Yogyakarta, Indonesia over the year 2020, and 345 leaves were collected and divided into three classes: canker, greening, and healthy. Citrus disease classification has four main stages, namely pre-processing, segmentation, feature extraction, and classification. Comparisons are made based on the normalization of the dataset and the KNN distance used. Given the results, dataset without normalization gets the best results with Hassanat distance KNN (k = 29) with an accuracy of 91.86%. A dataset with normalization receives the best results at Euclidean distance (k = 7) with an accuracy of 98.84%. These results affirm the efficiency of this the method in distinguishing diseases. As a result, this study can contribute to improving the quality of crops and reducing unnecessary expenses of pesticides, and finally could play a role in the economics of development.","PeriodicalId":51923,"journal":{"name":"Economic Annals-XXI","volume":" ","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Economic Annals-XXI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21003/ea.v197-06","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Social Sciences","Score":null,"Total":0}
引用次数: 0

Abstract

The citrus disease is a problem affecting the decrease of agricultural commodity yields. One way to determine disease in citrus is through the leaves. Leaves, as a place for photosynthesis, with the disease will cause stunted plant growth. This study revolves around an Agro-economic Analysis to classify citrus diseases based on leaf images by applying the Gray Level Co-occurrence Matrix (GLCM) extraction technology using K-Nearest Neighbor (KNN). To meet that aim, Otsu Thresholding segmentation is carried out to separate the disease’s image from the healthy leaves. This experiment was carried out in Yogyakarta, Indonesia over the year 2020, and 345 leaves were collected and divided into three classes: canker, greening, and healthy. Citrus disease classification has four main stages, namely pre-processing, segmentation, feature extraction, and classification. Comparisons are made based on the normalization of the dataset and the KNN distance used. Given the results, dataset without normalization gets the best results with Hassanat distance KNN (k = 29) with an accuracy of 91.86%. A dataset with normalization receives the best results at Euclidean distance (k = 7) with an accuracy of 98.84%. These results affirm the efficiency of this the method in distinguishing diseases. As a result, this study can contribute to improving the quality of crops and reducing unnecessary expenses of pesticides, and finally could play a role in the economics of development.
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
基于灰度共生矩阵的柑橘病害k近邻分类纹理特征提取技术:农业经济分析
柑橘病是影响农产品产量下降的一个问题。确定柑橘病害的一种方法是通过叶片。叶子作为光合作用的场所,携带这种疾病会导致植物生长发育迟缓。本研究围绕着一项农业经济分析,通过应用K近邻(KNN)的灰度共生矩阵(GLCM)提取技术,基于叶片图像对柑橘病害进行分类。为了实现这一目标,进行了Otsu阈值分割,将疾病图像与健康叶片分离。这项实验于2020年在印度尼西亚日惹进行,收集了345片叶子,分为三类:溃疡、绿化和健康。柑橘病害分类主要有四个阶段,即预处理、分割、特征提取和分类。基于数据集的归一化和所使用的KNN距离进行了比较。在给定结果的情况下,没有归一化的数据集在Hassanat距离KNN(k=29)下获得了最好的结果,准确率为91.86%。有归一化的数据集中在欧几里得距离(k=7)下获得的结果最好,准确度为98.84%。这些结果证实了该方法在区分疾病方面的有效性。因此,本研究有助于提高作物质量,减少不必要的农药费用,并最终在发展经济学中发挥作用。
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 去求助
来源期刊
Economic Annals-XXI
Economic Annals-XXI ECONOMICS-
CiteScore
1.50
自引率
0.00%
发文量
0
期刊介绍: The Economic Annals-XXI Journal – recognized in Ukraine and abroad scientific-analytic edition. Scientific articles of leading Ukrainian and other foreign scientists, postgraduate students and doctorates, deputies of Ukraine, heads of state and local authorities, materials of scientific conferences and seminars; reviews on scientific monographs, etc. are regularly published in this Journal.
期刊最新文献
Economic aspects of obtaining a functional creamy vegetable spread with a balanced fatty acid composition System characteristics and matrix tools for evaluating innovative business models of youth tourism Empirical study of business intelligence systems and their influence on innovation performance Phenomenology of the scientific system of Kazakhstan: a study of social and economic effects through the Hofstede’s five-dimensional model of cultural space and beyond Economic viability and market potential of combined intermediate moisture dairy products production in Kazakhstan
×
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