International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
TOMATO LEAF DETECTION AND REMEDY RECOMMENDATION SYSTEM USING MACHINE LEARNING AND IOT Deepika Singh NS1, Likitha DP2, Manasa M3, Tejaswini MR4, Mrs. Padmaja K5 1,2,3,4BE, Information Science and Engineering, GSSS Institute of Engineering and Technology for Women-Mysuru,
Karnataka, India
5 Associate Professor, Dept. of Information Science and Engineering, GSSS Institute of Engineering and Technology
for Women-Mysuru, Karnataka, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - This project presents an innovative approach to
This project addresses the pressing need for efficient and proactive monitoring of tomato plant health in agricultural settings. With the increasing challenges posed by plant diseases and the imperative to enhance crop yield, a comprehensive solution integrating cutting-edge technologies is proposed. The central components of the system include a Raspberry Pi equipped with a webcam and a DHT11 temperature sensor, providing a user-friendly platform for capturing vital leaf images and environmental data. Leveraging the Internet of Things (IoT), the collected information is securely transmitted to a cloud-based infrastructure, where a robust pipeline involving image processing and deep learning unfolds. The project's innovation lies in its utilization of a VGG19 deep learning model for disease classification, ensuring accurate and reliable identification of potential ailments affecting tomato plants. This integrated approach fosters a closed-loop system, as insights derived from the analysis, including disease categorization and recommended pesticide options, are promptly communicated back to users through the Raspberry Pi interface. By seamlessly merging IoT, image processing, and cloud computing, this project aims to empower farmers with timely, actionable information to make informed decisions about crop management. The overarching goal is to contribute to sustainable farming practices and optimize tomato crop yield in the face of evolving agricultural challenges.
tomato (biological name: Solanum lycopersicum) plant health monitoring, leveraging a synergy of image processing, IoT, and cloud technologies. The system centers around a Raspberry Pi equipped with a webcam and a DHT11 temperature sensor, enabling users to capture crucial leaf images and environmental data. Through secure transmission to a cloudbased infrastructure, the collected data undergoes comprehensive analysis. Initial image pre-processing enhances the quality of leaf images, followed by feature extraction and classification using a VGG19 deep learning model. The system adeptly identifies potential diseases affecting tomato plants, providing users with actionable insights. A unique feature of this project is its closed-loop functionality, as feedback, including disease classification and recommended pesticide options, is seamlessly relayed back to users via the Raspberry Pi. The cloud infrastructure, designed for scalability and reliability, ensures efficient data processing and model execution. By offering an accessible interface for farmers to monitor and address tomato plant health, this system contributes to improved crop management practices. The project's holistic integration of cutting-edge technologies is poised to empower agricultural stakeholders with timely, accurate, and actionable information, ultimately fostering sustainable farming practices and enhancing tomato crop yield. Key Words: IoT, Cloud technologies, Raspberry Pi, DHT11 temperature sensor, Data analysis, Image preprocessing, Feature extraction, VGG19 deep learning model
2.PROBLEM STATEMENT Given a dataset of tomato leaf images, the task is to develop a machine learning model that can accurately classify the images into different disease categories. The goal is to help farmers quickly identify and treat diseased tomato plants, thereby improving crop yield and reducing losses.
1.INTRODUCTION In most African and Asian nations, agriculture has historically been the main source of wealth. The extensive commercialization of agriculture has had a profound effect on the environment. Identifying plant diseases is one of the most urgent problems related to agriculture. Early disease identification helps stop the illness from spreading to other plants, which could cause significant financial losses. Plant diseases can have a wide range of effects, from mild symptoms to the complete loss of plantations, which has a big effect on the agricultural economy.
© 2024, IRJET
|
Impact Factor value: 8.226
3.PROPOSED SYSTEM The proposed system builds upon the foundation of the existing framework aiming to further enhance its capabilities and usability. It focuses on refining the image processing algorithms to improve disease detection accuracy, exploring additional IoT sensors for capturing more comprehensive environmental data, and optimizing the cloud infrastructure for scalability and efficiency this will incorporates a
|
ISO 9001:2008 Certified Journal
|
Page 2293