Plant disease detection using Machine Learning
Date
2023
Student ID
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Plant disease detection is a critical aspect of precision agriculture, facilitating early intervention to minimize crop losses and ensure food security. This research leverages machine learning techniques, specifically ResNet50, Nasnet, and a custom Fewshot learning model, for accurate identification of plant diseases based on the PlantVillage dataset. The study addresses the limitations of existing research by exploring the effectiveness of Fewshot learning and conducting a comprehensive comparative analysis of multiple model architectures. Through extensive experimentation and evaluation, the ResNet50 model emerged as the most accurate, achieving a validation accuracy of 96%. The Fewshot learning model, while demonstrating lower accuracy, showcased potential in scenarios with limited labeled examples. The research contributes to the advancement of plant disease detection technologies, offering insights into the practical implications of different model architectures and paving the way for future developments in sustainable and resilient agriculture.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University