SkinScanAI

Overview

This project aims to provide a solution for skin condition analysis using AI. While the initial description is absent, this README will guide you through understanding the project's current structure, technologies involved, and setup process.

Key Features & Benefits

• AI-Powered Analysis: Utilizes a pre-trained model for skin condition assessment.
• Web Interface: Provides a user-friendly frontend for interacting with the system.
• Containerized Deployment: Leverages Docker for easy and consistent deployment.
• Modular Architecture: Separates the frontend, backend, and AI model for maintainability.

Prerequisites & Dependencies

Before you begin, ensure you have the following installed:

• Docker: https://www.docker.com/get-started
• Docker Compose: Generally comes with Docker Desktop, or can be installed separately.
• Node.js: https://nodejs.org/ (Required for Frontend Development)
• Python 3.11+: Recommended for Backend and AI Model Development

Installation & Setup Instructions

Follow these steps to get the project up and running:

1. Clone the Repository:

   git clone <repository_url>
   cd SkinScanAI
   

2. Build and Run with Docker Compose:

   docker-compose up --build
   

   This command will build the Docker images for the frontend, backend, and start all services. It might take a while on the first run as it downloads and installs the necessary dependencies.

3. Access the Application:

   Once the Docker containers are running, you can access the application in your web browser at http://localhost:3000. (The frontend port is configured to 3000, but check docker-compose.yml to confirm).

Detailed Setup (Optional - Individual Components)

If you prefer setting up each component individually, follow these steps:

A. AI Model (Optional - Mostly for development)

1. Navigate to the AI-model directory:

   cd AI-model
   

2. Create a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Linux/macOS
   venv\Scripts\activate  # On Windows
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Run the script (for testing/development):

   python script.py
   

B. Backend (Optional - Mostly for development/customization)

1. Navigate to the backend directory:

   cd ../backend
   

2. Create a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Linux/macOS
   venv\Scripts\activate  # On Windows
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Set up environment variables (if needed). You may need to configure the path to the model.

5. Run the backend application:

   python app.py
   

   This will typically start the Flask server on port 5000.

C. Frontend (Optional - Mostly for development/customization)

1. Navigate to the frontend directory:

   cd ../frontend
   

2. Install dependencies:

   npm install
   

3. Start the development server:

   npm run dev
   

   This will usually start the Next.js development server on port 3000.

Usage Examples & API Documentation

Frontend Usage

The frontend provides a user interface for uploading skin images and receiving analysis results. Detailed instructions for usage will be included in the frontend's own README.md file within the frontend directory.

Backend API

The backend provides the following API endpoint:

• /predict (POST): Accepts an image file and returns the prediction from the AI model.

  • Request:
    • Content-Type: multipart/form-data
    • File field: image
  • Response:

    {
        "prediction": "Diagnosis Result",
        "confidence": 0.87
    }
    

  The confidence value represents the model's certainty in the prediction.

  • Example (using curl):

    curl -X POST -F "image=@/path/to/image.jpg" http://localhost:5000/predict
    

Configuration Options

Backend

• Model Path: The path to the model_acc_0.87.pth file can be configured as an environment variable. This allows you to use a different model or specify an absolute path. Example:

  MODEL_PATH=/path/to/your/model.pth
  

  You will need to modify the app.py file to read this environment variable.
• CORS Configuration: The CORS settings in app.py can be adjusted to restrict access to specific origins or allow all origins.

Frontend

• The frontend configuration can be found in next.config.ts. You might want to change the backend URL if it's hosted on a different server.

Contributing Guidelines

We welcome contributions to this project! Please follow these guidelines:

1. Fork the repository.
2. Create a new branch for your feature or bug fix.
3. Implement your changes.
4. Write tests to ensure your changes are working correctly.
5. Submit a pull request with a clear description of your changes.

License Information

License not specified.

Acknowledgments

• The AI model is based on publicly available datasets and pre-trained architectures.
• The frontend utilizes the Next.js framework.
• The backend uses Flask and PyTorch.