{"title":"A Lightweight Deep Learning Model for Agricultural Pathology","authors":"K. S. S. Sai, M. Nandeesh, M. Pushpa","doi":"10.1109/ICDSIS55133.2022.9915842","DOIUrl":null,"url":null,"abstract":"A technique to determine diseases in agricultural crops from leaf images using deep convolutional neural networks is proposed. 12 different diseases in potato, tomato and bell pepper crops are determined from leaf images. As many methods proposed in the existing literature are computationally expensive and are restricted to specific plant species, the proposed technique is capable of determining diseases in multiple crops using a single neural network based model while also minimizing computational complexity. The method obtains an F1 score, accuracy, precision, of 93.66%, 93.72%, 93.57% respectively. Enhancements in the performance are seen when compared to the already existing methods.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDSIS55133.2022.9915842","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
A technique to determine diseases in agricultural crops from leaf images using deep convolutional neural networks is proposed. 12 different diseases in potato, tomato and bell pepper crops are determined from leaf images. As many methods proposed in the existing literature are computationally expensive and are restricted to specific plant species, the proposed technique is capable of determining diseases in multiple crops using a single neural network based model while also minimizing computational complexity. The method obtains an F1 score, accuracy, precision, of 93.66%, 93.72%, 93.57% respectively. Enhancements in the performance are seen when compared to the already existing methods.