Research Article
An Accurate Plant Disease Detection Technique Using Machine Learning
@ARTICLE{10.4108/eetiot.4963, author={Sai Sharvesh R and Suresh Kumar K and C. J. Raman}, title={An Accurate Plant Disease Detection Technique Using Machine Learning}, journal={EAI Endorsed Transactions on Internet of Things}, volume={10}, number={1}, publisher={EAI}, journal_a={IOT}, year={2024}, month={1}, keywords={Agriculture, Plant diseases detection, Image processing, Machine learning}, doi={10.4108/eetiot.4963} }
- Sai Sharvesh R
Suresh Kumar K
C. J. Raman
Year: 2024
An Accurate Plant Disease Detection Technique Using Machine Learning
IOT
EAI
DOI: 10.4108/eetiot.4963
Abstract
INTRODUCTION: Plant diseases pose a significant threat to agriculture, causing substantial crop and financial losses. Modern technologies enable precise monitoring of plant health and early disease identification. Employing image processing, particularly Convolutional Neural Network (CNN) techniques, allows accurate prediction of plant diseases. The aim is to provide an automated, reliable disease detection system, aiding professionals and farmers in timely action to prevent infections and reduce crop losses. Integrating cutting-edge technologies in agriculture holds vast potential to enhance profitability and production. OBJECTIVES: The primary focus lies in developing an automated system proficient in analysing plant images to detect disease symptoms and classify plants as healthy or disease affected. The system aims to simplify plant disease diagnostics for farmers, providing essential information about leaf name, integrity, and life span. METHODS: The method aims to empower farmers by enabling easy identification of plant diseases, providing essential details like disease name, accuracy level, and life span. The CNN model accurately gauges the system's accuracy level. It further streamlines the process by offering a unified solution through a user-friendly web application, eliminating the need for separate interventions for affected leaves. the system saves farmers time by delivering crucial information directly. RESULTS: The Proposed web application proves to be a comprehensive solution, eliminating the need for farmers to search for separate interventions for affected leaves. The machine learning model exhibits a noteworthy accuracy of 96.67%, emphasizing its proficiency in making correct predictions for the given task. CONCLUSION: In conclusion, the paper successfully employed a CNN algorithm for precise plant disease prediction. With the proposed model deployment, farmers can easily access information about plant diseases, their life span, and preventive measures through the web application. By detecting illnesses early, farmers can promptly take remedial actions to mitigate sicknesses and minimize crop losses. The integrated approach holds promise for advancing agricultural practices and ensuring sustainable crop management.
Copyright © 2024 Sai Sharvesh. R. et al., licensed to EAI. This is an open access article distributed under the terms of the CC BYNC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.