terry007-cyber/Plant-Disease-Detection

This project is a lightweight, web-based crop disease detection system powered by machine learning. Farmers and students can upload plant images to receive real-time disease diagnoses, treatment suggestions, and educational resources. Designed for low-bandwidth and mobile use in rural Ethiopia. # Plant Disease Detection: An AI-Powered Agricultural Tool 🌿🔬 ## Project Mission To empower **farmers, students, and agricultural researchers** with an accessible, AI-driven tool for the rapid and accurate identification of plant diseases. Our mission is to leverage technology to support sustainable agriculture, facilitate learning, and encourage data-driven research in plant pathology. By providing instant diagnostics, we aim to help protect crop yields, reduce economic losses, and promote responsible disease management practices. --- --- ## Why This Project Matters This tool is designed to be a bridge between advanced technology and practical agriculture, offering distinct benefits for its core users: - **For Farmers:** Provides a crucial "first alert" system. Get an immediate, on-the-spot analysis of a suspicious plant leaf, enabling faster decision-making for treatment and quarantine, potentially saving a significant portion of a harvest. - **For Students & Educators:** Serves as a dynamic, hands-on learning resource for studies in agronomy, botany, and computer science. It connects theoretical knowledge of plant diseases with practical, visual examples and the real-world application of artificial intelligence. - **For Researchers:** Offers a robust, extensible platform for plant pathology research. The existing models can be analyzed, improved, or used as a baseline. The framework can be easily adapted to include new plant species or disease categories, facilitating new avenues of study. ## How It Works: The Technology Pipeline The application follows a simple yet powerful workflow to provide a diagnosis: 1. **Image Upload:** The user selects and uploads an image of a plant leaf through the simple web interface. 2. **Backend API Request:** The frontend sends the image data to the secure, high-performance Python backend built with FastAPI. 3. **Image Preprocessing:** The backend prepares the image for the model by resizing it to the requir …