International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 08|Aug 2023
p-ISSN: 2395-0072
www.irjet.net
An Innovative Approach for Tomato Leaf Disease Identification and its Beneficial Impacts 1
2
Laeeq Sana , Dr. Shantkumari Patil 1
Student, Dept. of Computer Science and Engineering, Sharnbasva University, Kalaburagi ,Karnataka ,India Associate.Professor, Dept. of Computer Science and Engineering, Sharnbasva University, Kalaburagi, Karnataka, India ------------------------------------------------------------------------***------------------------------------------------------------------------2
Abstract The accurate identification and early detection of tomato leaf diseases are crucial for maintaining crop yield and quality. In this study, we present an innovative approach for tomato leaf disease identification utilizing advanced image processing and machine learning techniques. Our methodology involves the development and training of a Convolutional Neural Network (CNN) model on a comprehensive dataset of tomato leaf images showcasing various disease symptoms. Through rigorous experimentation and validation, our proposed approach achieves a high level of accuracy in classifying different types of tomato leaf diseases. The integration of our method into existing agricultural practices demonstrates its potential for timely disease detection, reducing crop losses, and optimizing resource allocation. Additionally, we explore the beneficial impacts of our approach on sustainable agriculture, including minimized pesticide usage and improved resource efficiency. This research contributes to the field by offering a practical solution for automating the detection of tomato leaf diseases, leading to enhanced disease management and more sustainable agricultural practices. The results underscore the potential of modern technology to revolutionize crop health monitoring and ensure food security.
Keywords: Tomato leaf diseases, disease identification, Convolutional Neural Network, image processing, machine learning, early detection, agriculture, sustainable practices, crop health, food security.
1. INTRODUCTION Tomato plants (Solanum lycopersicum) are among the most widely cultivated and economically important crops globally, contributing significantly to both food security and agricultural economies. However, the susceptibility of tomato plants to various diseases poses a substantial challenge to sustainable cultivation. Timely identification and effective management of these diseases are pivotal for ensuring optimal yield, maintaining crop quality, and reducing economic losses within the agricultural sector.Traditional methods of disease detection often rely on manual visual inspection by agricultural experts, which © 2023, IRJET
Impact Factor value: 8.266
can be time-consuming, labor-intensive, and prone to subjectivity. Moreover, delays in disease detection can lead to rapid disease progression, exacerbating the impact on crop yield and quality. Thus, the development of accurate and automated methods for early disease identification is imperative for modernizing agricultural practices and safeguarding crop health. In response to these challenges, this project introduces an innovative approach for the identification of tomato leaf diseases. Leveraging advancements in image processing and machine learning, our proposed methodology employs a Convolutional Neural Network (CNN) model to analyze digital images of tomato leaves and categorize them based on disease symptoms. The utilization of CNNs capitalizes on their ability to extract intricate features from images, enabling robust disease classification. Throughout this project, we delve into the technical intricacies of our approach, detailing the design and training of the CNN model on a comprehensive dataset of annotated tomato leaf images. We also highlight the experimental setup, validation procedures, and performance metrics used to assess the accuracy and efficiency of our disease identification method. Furthermore, this project goes beyond technical considerations and explores the broader impacts of our approach on sustainable agriculture. By enabling early disease detection, our method holds the potential to reduce the need for excessive pesticide application, thereby minimizing environmental harm and promoting ecofriendly agricultural practices. Additionally, the economic benefits of timely disease management and increased crop yield contribute to enhancing food security and the livelihoods of farmers. In the subsequent sections of this report, we delve into the methodology, experimental results, and discuss the implications of our innovative approach for the future of tomato crop management. Through the amalgamation of technology and agriculture, this project aims to revolutionize disease detection strategies and contribute to the advancement of more resilient and sustainable food production systems.
2. Related Works Article[1]"Deep Learning Approaches for Plant Disease Detection and Diagnosis" by Kamilaris, Andreas, et al. in 2018
ISO 9001:2008 Certified Journal
|
Page 488