Umax AI - Facial Analysis Website

A modern web application that provides AI-powered facial analysis and personalized looksmaxing recommendations using advanced computer vision and natural language processing.

🌟 Features

• AI-Powered Facial Analysis: Advanced facial attribute detection using InsightFace
• Personalized Recommendations: Custom looksmaxing plans generated by GPT-4
• Modern Web Interface: Responsive design with drag-and-drop image upload
• Real-time Processing: Fast analysis with visual feedback
• Privacy-Focused: Images are not stored on the server

📊 Analysis Metrics

The system uses advanced AI models to analyze comprehensive facial attributes:

• Beauty Score: Overall beauty assessment using specialized AI models
• Overall Attractiveness: Composite attractiveness score
• Skin Analysis:
  • Skin clarity and texture quality
  • Acne detection and severity assessment
  • Overall skin health evaluation
• Hair Analysis:
  • Hair health and density assessment
  • Hair volume and quality analysis
  • Hairline quality evaluation
• Additional Metrics: Age, gender, and other facial characteristics

🚀 Quick Start

Prerequisites

• Python 3.8 or higher
• OpenAI API key
• Modern web browser

Installation

1. Clone or download the project files

2. Install Python dependencies:

   pip install -r requirements.txt

3. Set up your OpenAI API key:

   export OPENAI_API_KEY="your-api-key-here"

   Or on Windows:

   set OPENAI_API_KEY=your-api-key-here

4. Start the backend server:

   python start_server.py

   Or directly:

   python api.py

5. Open the website:

   • Open index.html in your web browser
   • The website will automatically connect to the backend server

🏗️ Project Structure

Umax2/
├── 📄 Frontend Files
│   ├── index.html          # Main website interface
│   ├── styles.css          # Website styling
│   └── script.js           # Frontend JavaScript logic
│
├── 🧠 Backend Components
│   ├── api.py              # Flask REST API server
│   ├── pipeline.py         # Main analysis pipeline
│   ├── face_detector.py    # Face detection using dlib
│   ├── attribute_predictor.py # Facial analysis using InsightFace
│   ├── rag_retriever.py    # Knowledge base retrieval
│   ├── plan_generator.py   # AI-powered plan generation
│   └── config.py           # Configuration settings
│
├── 🔧 Utilities
│   ├── utils.py            # Helper functions
│   ├── main.py             # Command-line interface
│   └── start_server.py     # Server startup script
│
└── 📚 Documentation
    ├── README.md           # This file
    └── requirements.txt    # Python dependencies

🎯 Usage

1. Start the Server: Run python start_server.py
2. Open Website: Open index.html in your browser
3. Upload Image: Drag and drop or click to select a photo
4. Analyze: Click "Analyze Face" to process the image
5. Review Results: View detailed analysis and personalized recommendations

📱 API Endpoints

POST /analyze

Analyze a facial image and return detailed attributes and recommendations.

Request:

• Form data with image file

Response:

{
  "success": true,
  "detected_attributes": {
    "attractiveness": 0.75,
    "overall_score": 3.8,
    "skin_clarity_score": 0.82,
    "skin_texture_quality": 0.68,
    "overall_skin_health": 0.75,
    "acne_severity": 0.25,
    "hair_health_score": 0.78,
    "hair_density": 0.65,
    "hair_volume": 0.70,
    "overall_hair_score": 0.71,
    "hairline_quality": 0.83,
    "hair_type": "straight",
    "hair_color": "brown",
    "age": 25,
    "gender": "Male"
  },
  "analysis": {
    "status": "good",
    "message": "You have one area to work on: Acne Severity.",
    "strengths": [...],
    "weaknesses": [...],
    "advice": [...]
  },
  "personalized_plan": "## LOOKSMAXING PLAN\n...",
  "face_crop_b64": "data:image/jpeg;base64,..."
}

GET /health

Check server health and configuration status.

GET /

API information and available endpoints.

⚙️ Configuration

Key settings can be modified in config.py:

class Config:
    # API Configuration
    OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
    OPENAI_MODEL = "gpt-4o-mini"
    
    # Analysis Settings
    FACE_SIZE = (224, 224)
    LOW_THRESHOLD = 0.4
    HIGH_THRESHOLD = 0.7
    
    # Server Settings
    API_PORT = 5000
    DEBUG_MODE = True

🔧 Troubleshooting

Common Issues

1. "Cannot connect to backend server"

   • Ensure the Flask server is running (python api.py)
   • Check if port 5000 is available
   • Verify no firewall is blocking the connection

2. "OPENAI_API_KEY not set"

   • Set the environment variable: export OPENAI_API_KEY="your-key"
   • Restart the server after setting the key

3. "No face detected"

   • Use a clear, front-facing photo
   • Ensure good lighting
   • Try a different image format (JPG, PNG)

4. Dependencies missing

   • Run: pip install -r requirements.txt
   • Ensure Python 3.8+ is being used

Browser Compatibility

Tested on:

• ✅ Chrome 90+
• ✅ Firefox 88+
• ✅ Safari 14+
• ✅ Edge 90+

🔒 Privacy & Security

• No Data Storage: Images are processed in memory and not saved
• Secure Transmission: All API calls use standard HTTP security
• Local Processing: Face detection happens on your server
• API Key Protection: OpenAI key is server-side only

🛠️ Development

Adding New Features

1. Backend: Modify pipeline components in their respective files
2. Frontend: Update HTML, CSS, and JavaScript as needed
3. API: Add new endpoints in api.py

Testing

# Test backend components
python main.py path/to/test/image.jpg

# Test API directly
curl -X POST -F "image=@test.jpg" http://localhost:5000/analyze

📋 Dependencies

Backend

• Flask - Web framework
• OpenAI - GPT integration
• OpenCV - Image processing
• InsightFace - Facial analysis
• ChromaDB - Vector database
• SentenceTransformers - Text embeddings
• NumPy - Numerical computations

Frontend

• Pure HTML/CSS/JavaScript
• Font Awesome icons
• Google Fonts (Inter)

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

📄 License

This project is for educational and research purposes. Please respect privacy and obtain consent before analyzing facial images.

🆘 Support

For issues or questions:

1. Check the troubleshooting section
2. Verify your setup matches the requirements
3. Review server logs for error details
4. Ensure all dependencies are properly installed

---

Built with ❤️ using AI and modern web technologies