A Flutter mobile application that uses AI and environmental sensors to analyze crop health and provide eco-friendly treatment recommendations.

• Live Camera Preview: Capture high-quality images of crop leaves
• AI-Powered Analysis: Analyze leaf images for signs of disease, deficiency, or stress
• Environmental Monitoring: Real-time humidity and temperature tracking
• Risk Assessment: Comprehensive risk scoring based on visual and environmental factors
• Eco-Friendly Solutions: Organic and sustainable treatment recommendations
• Scan History: Track and review past analyses
• Offline Ready: Works without internet connection

• Healthy crops
• Early Fungal Stress
• Nitrogen Deficiency
• Bacterial Spot
• Viral Infection
• Potassium Deficiency
• Phosphorus Deficiency
• Magnesium Deficiency

• Flutter SDK (>=3.0.0)
• Android Studio or Xcode for mobile development
• Camera-enabled device for testing

1. Clone the repository:

git clone <repository-url>
cd crop_health_app

2. Install dependencies:

flutter pub get

3. Generate Hive adapters:

flutter packages pub run build_runner build

4. Run the app:

flutter run

The app requires the following permissions:

• Camera: To capture leaf images
• Storage: To save analysis results
• Bluetooth: To connect to environmental sensors (optional)
• Location: For Bluetooth device discovery

• CaptureScreen: Camera interface with environmental controls
• ResultScreen: Analysis results with recommendations
• HistoryScreen: Past scan history
• AboutScreen: App information and sustainability focus

• TFLiteService: AI model integration for image analysis
• SensorService: Environmental sensor data management
• StorageService: Local data persistence with Hive

• ScanResult: Data model for storing analysis results

The app supports both simulated and real environmental sensors:

• Interactive sliders for humidity (0-100%) and temperature (10-40°C)
• Realistic value variations for testing

• Connects to ESP32-based environmental sensors
• Real-time humidity and temperature readings
• Automatic fallback to simulation if disconnected

This app promotes sustainable agriculture through:

• Early disease detection to prevent crop loss
• Organic treatment recommendations
• Reduced pesticide dependency
• Soil health preservation
• Cost-effective prevention strategies

1. Update assets/models/labels.txt with new condition names
2. Add treatment recommendations to assets/data/actions.json
3. Update the TFLiteService analysis logic
4. Test with sample images

The app uses a nature-inspired color palette:

• Primary Green: #4CAF50
• Dark Green: #2E7D32
• Light Background: #F8F9FA
• Accent Colors: Blue (#2196F3), Orange (#FF9800)

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

This project is licensed under the MIT License - see the LICENSE file for details.

• Inspired by nature's early warning systems
• Built with sustainability and farmer welfare in mind
• Designed for accessibility and ease of use