A collection of real-time Computer Vision projects built using Python, OpenCV, and MediaPipe. This repository demonstrates how hand tracking can be used to create natural Human-Computer Interaction (HCI) applications such as controlling the system volume and moving the mouse with simple hand gestures.
- ✋ Real-time hand detection and tracking
- 🎯 21 hand landmark detection using MediaPipe
- 🖱️ Virtual Mouse Control
- 🔊 Hand Gesture Volume Control
- 📈 Live FPS display
- ♻️ Reusable Hand Tracking Module
ComputerVision/
│
├── HandTrakingModule.py # Custom reusable hand tracking module
├── VirtualMouseControl.py # Control mouse using hand gestures
├── VolumeHandControl.py # Control Windows volume using finger distance
├── ex.py # Testing / experimental file
│
├── requirements.txt # Project dependencies
├── README.md # Project documentation
├── LICENSE # License
├── .gitignore # Ignored files
Control your Windows system volume using only your hand.
- Detects thumb and index finger
- Calculates the distance between fingertips
- Maps the distance to Windows master volume
- Displays volume percentage
- Smooth real-time interaction
- Python
- OpenCV
- MediaPipe
- NumPy
- PyCAW
Control the mouse cursor using hand gestures captured through the webcam.
- Move mouse cursor
- Gesture-based clicking
- Smooth cursor movement
- Real-time hand tracking
- Python
- OpenCV
- MediaPipe
- PyAutoGUI
Clone the repository
git clone https://github.com/your-username/ComputerVision-py.gitGo into the project folder
cd ComputerVisionInstall the required packages
pip install -r requirements.txtpython VolumeHandControl.pypython VirtualMouseControl.py- OpenCV
- MediaPipe
- NumPy
- PyCAW
- PyAutoGUI
- Comtypes
Install everything with
pip install -r requirements.txtWhile building these projects I learned:
- Computer Vision fundamentals
- Image processing with OpenCV
- Hand tracking using MediaPipe
- Gesture recognition
- Human-Computer Interaction (HCI)
- Windows Audio API integration
- Real-time application development
- Brightness control
- Gesture-based media player
- AI virtual painter
- Air keyboard
- Hand gesture presentation controller
- Multi-hand gesture recognition
Contributions, ideas, and suggestions are always welcome.
Feel free to fork the repository and submit a pull request.
If you found this project helpful, consider giving it a Star ⭐ on GitHub.
This project is licensed under the MIT License.