{"title":"Fuzzy detection orange tree leaves diseases using a co-occurrence matrix-based K-nearest neighbours classifiers","authors":"F. Jakjoud, A. Hatim, Abella Bouaddi","doi":"10.1504/ijkesdp.2019.10025585","DOIUrl":null,"url":null,"abstract":"The improvement of production efficiency in the farming environment is nowadays of a great interest in the agriculture industry. Several techniques and technologies are used to overcome the main problems facing the developments on this field. In this paper, the farms image processing-based automatic monitoring is treated. We propose an image processing approach for lemon tree leaves diseases. Our approach is a combination of a fuzzy decision maker and KNN classifiers based on Haralick parameters extracted from the co-occurrence matrix. The testing results are very satisfactory and the efficiency of our system could reach aver than 90% for a limited database.","PeriodicalId":347123,"journal":{"name":"Int. J. Knowl. Eng. Soft Data Paradigms","volume":"66 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Knowl. Eng. Soft Data Paradigms","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/ijkesdp.2019.10025585","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
The improvement of production efficiency in the farming environment is nowadays of a great interest in the agriculture industry. Several techniques and technologies are used to overcome the main problems facing the developments on this field. In this paper, the farms image processing-based automatic monitoring is treated. We propose an image processing approach for lemon tree leaves diseases. Our approach is a combination of a fuzzy decision maker and KNN classifiers based on Haralick parameters extracted from the co-occurrence matrix. The testing results are very satisfactory and the efficiency of our system could reach aver than 90% for a limited database.