Multiclass Detection of Citrus Leaf Diseases Using YOLO

Project Code :TCMAPY2304

Objective

The primary objective of this project is to develop an efficient and accurate system for detecting citrus leaf diseases. The system will leverage a deep learning-based detection model, specifically utilizing YOLOv12, to classify various citrus leaf diseases. To ensure accessibility and ease of use for farmers, researchers, and agricultural professionals, a user-friendly web application will be created. This application will feature essential modules such as user registration, disease prediction, and logout functionality. The system will be trained and validated using a citrus leaf disease dataset sourced from Roboflow. The goal is to enhance both the accuracy and speed of disease detection, providing valuable results that can aid in better decision-making. Additionally, the system will offer actionable insights for the detected diseases, including possible treatments and recommendations for disease management. The front-end will be built using HTML, CSS, and JavaScript, while Streamlit will be utilized for the back-end, ensuring seamless integration and interaction across the platform.

Abstract

The project " Multiclass Detection of Citrus Leaf Diseases Using YOLO " aims to develop an intelligent system for detecting and classifying citrus leaf diseases in real-time. By leveraging advanced deep learning techniques, the project focuses on the identification of various leaf diseases using the YOLOv12 algorithm, offering a fast and accurate solution for disease detection. The system integrates multiple modules, including user authentication (Register, Login), disease classification, and prediction features. The front-end is developed using HTML, CSS, and JS, while the back-end is powered by Python with Streamlit for seamless interaction. The dataset used for training the model comes from the publicly available "Citrus Leaf" dataset on Roboflow. This system aims to assist farmers, researchers, and agricultural professionals by providing rapid disease identification and actionable insights, contributing to the optimization of crop management practices.

Keywords: Citrus leaf, disease detection, YOLOv12, deep learning, real-time, classification, prediction, agriculture, Streamlit, machine learning.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.