HomeProjectsHackathonsEventsWorkBlogTimeline

FitSnap

AI powered clothing size prediction along with overlays to try out clothes virtually using AR tech.

HackX 3.0

๐ŸŽ“ Narsee Monjee Institute of Management Studies (NMIMS), Navi Mumbai

๐Ÿ“Œ Navi Mumbai, Maharashtra

๐Ÿš€ 24hr Hackathon Project

๐Ÿฅˆ 2nd
dashboard
overlay
profile

FitSnap - Personalized Virtual Wardrobe

FitSnap is an AI-powered application that not only predicts your shoulder width, chest, and waist measurements based on your height but also offers a unique social experience. Engage with a Tinder-like interface to swipe right on outfits you love from other users and virtually try them on by overlaying the selected clothing onto your photo.

Features

  • Accurate Measurement Predictions: Utilizes advanced AI models to estimate key body measurements.
  • Personalized Size Recommendations: Suggests optimal clothing sizes tailored to your body profile.
  • Social Outfit Discovery: Explore and like outfits from other users with an intuitive swipe interface.
  • Virtual Try-On: Overlay liked outfits onto your photo using cutting-edge image processing techniques.

Virtual Try-On Technology

FitSnap's virtual try-on feature employs a combination of advanced technologies:

  1. Clothing Segmentation with U2NET: Segments clothing items from images to isolate them for overlay.
  2. Pose Estimation with MediaPipe: Detects and aligns body joints to ensure accurate placement of clothing.
  3. Image Processing with OpenCV: Overlays segmented clothing onto user photos, adjusting for pose and alignment.

Installation

  1. Clone the Repository:
    git clone https://github.com/jaykerkar0405/FitSnap.git
    
  2. Navigate to the Project Directory:
    cd FitSnap
    
  3. Install Dependencies:
    • For the backend:
      cd backend
      pip install -r requirements.txt
      
    • For the frontend:
      cd frontend
      npm install
      

Usage

  1. Start the Backend Server:
    cd backend
    python app.py
    
  2. Launch the Frontend Application:
    cd frontend
    npm start
    
  3. Access the Application: Open your browser and navigate to http://localhost:3000 to use FitSnap.

Contributing

We welcome contributions! Please follow these steps:

  1. Fork the Repository: Click on the 'Fork' button at the top right of this page.
  2. Create a New Branch: Use git checkout -b feature-branch-name.
  3. Make Your Changes: Implement your feature or fix.
  4. Commit Changes: Use git commit -m 'Description of your changes'.
  5. Push to Your Fork: Use git push origin feature-branch-name.
  6. Submit a Pull Request: Navigate to the original repository and click on 'New Pull Request'.

Acknowledgements

Special thanks to the contributors: Sundaram Krishnan, Yash Kolekar, Aayush Nair, Jay Kerkar.