TULASI LEAF DISEASE PREDICTION

This project aims to develop an optimized solution for the classification and detection of Tulasi leaf diseases using advanced deep learning techniques. The dataset includes various categories of disease types, such as bacterial, fungal, and pest-related issues, alongside healthy leaf data. The target variable, "Disease Type," is classified into four categories: Bacterial, Fungal, Healthy, and Pests. To accurately identify and classify these disease types, the Yolov11 (You Only Look Once) algorithm is employed for object detection and classification. This deep learning model offers a fast and efficient approach to detecting specific leaf conditions and provides high accuracy in distinguishing between the disease classes. The model’s performance is evaluated using precision, recall, and F1-score metrics. A user-friendly web application is developed using Streamlit, enabling users to upload images of Tulasi leaves for disease detection. This solution aids in early diagnosis of Tulasi leaf diseases, helping farmers and researchers take timely actions to prevent crop damage, optimize yield, and improve overall agricultural productivity.

Keywords: Tulasi Leaf Disease Detection, Yolov11, Machine Learning, Deep Learning, Image Classification, Streamlit, Predictive Modeling, Disease Classification, Precision Agriculture, Fungal Detection, Pest Detection, Bacterial Detection.