RealTime Plant Disease Detection Using AI

This project presents a real-time plant leaf disease detection system based on a custom-trained YOLOv11 model, leveraging deep learning and computer vision for precise and rapid identification of plant health status. Unlike approaches that rely on pretrained models or transfer learning, this system is developed entirely using a YOLOv11 model trained from scratch on a labeled dataset of plant leaf images. The model is optimized to detect and classify whether a leaf is healthy or exhibits signs of disease, ensuring high accuracy and low latency in prediction.

To provide a user-friendly experience, the system is integrated into an interactive web application using Streamlit. It supports both static image uploads and real-time webcam-based input, making it accessible and practical for field use, especially by farmers and agricultural experts. This dual-mode capability ensures that users can diagnose plant health instantly without requiring advanced hardware or technical expertise.

By deploying a fully customized YOLOv11 model alongside a lightweight and intuitive interface, this project delivers a scalable, low-cost solution for plant disease monitoring. It promotes early intervention, enhances crop health management, and contributes to smart farming initiatives.

Keywords: Plant Disease Detection, YOLOv11, Deep Learning, Computer Vision, Real-Time Prediction, Streamlit, Custom Training, Leaf Classification, Image Processing, Precision Agriculture, Smart Farming, Non-Pretrained Model, Webcam Detection.