Crop Disease Detector

A comprehensive full-stack application designed to detect and classify crop diseases using machine learning. The project is split into three decoupled services:

• Frontend: A sleek React user interface for image uploads and results display.
• Backend API: A fast Node.js Express server to handle uploads and business logic.
• ML Service: A robust Python FastAPI backend dedicated to running inference using TensorFlow.

---

🏗️ Architecture details

1. Frontend (/frontend)

• Tech Stack: React 18, Tailwind CSS, Axios, React Router v6.
• Role: Provides the user-facing interface (agrilens-frontend) to seamlessly upload plant photos and analyze results.
• Port: Runs on http://localhost:3000 by default.

2. Backend (/backend)

• Tech Stack: Node.js, Express, Mongoose (MongoDB), Multer.
• Role: Acts as the main API layer. It coordinates file uploads, handles database connections, stores images in backend/uploads/, and manages CORS / security boundaries with Helmet.
• Port: Runs on http://localhost:5001.

3. Machine Learning Service (/ml_service)

• Tech Stack: Python 3.8+, FastAPI, TensorFlow, Pillow, OpenCV.
• Role: Dedicated ML inference server. Reads .h5 models from the ml_service/models/ directory, processes images, and serves predictions via POST /predict/{model_name}.
• Port: Runs on http://localhost:8000.

---

🚀 Getting Started

Prerequisites

• Node.js (v16.0.0 or newer)
• Python (v3.8 or newer)
• MongoDB (Local or Atlas URI inside backend/.env)
• Pre-trained .h5 model files.

One-Click Startup (Recommended)

To streamline launching all three services at once:

1. Copy your trained TensorFlow model files (.h5) into the ml_service/models/ folder.
2. Run the start.bat script located in the root directory.

The script will automatically verify your environment, install missing Node/Python packages across all three folders, spin up each service, and launch the web interface in your browser.

---

Manual Setup

If you prefer to start each service independently in separate terminal windows:

1. ML Service

cd ml_service
pip install -r requirements.txt
python simple_server.py

2. Node.js Backend

cd backend
npm install
npm run dev

3. React Frontend

cd frontend
npm install
npm start