Skip to content

CuriousCoder25/Gestures-AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

15 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

🎨 AI-powered Hand Gesture Whiteboard βœ‹ πŸš€ Overview Welcome to the AI-powered Hand Gesture Whiteboard! This web-based application allows you to draw in the air using your index finger β€” no mouse or stylus required. It captures your hand movements in real-time and converts gestures into drawings on a digital canvas.

Built using cutting-edge technologies like TensorFlow.js and MediaPipe Hands, this app enables you to create drawings with the power of AI and hand gesture recognition.


🧠 Features

  • ✍️ Draw with your index finger – Control your drawing by simply moving your finger.
  • 🧽 Toggle between Drawing and Erasing modes – Easily switch between drawing and erasing.
  • πŸŽ₯ Real-time hand tracking – Tracks your hand movements through the webcam in real-time.
  • 🧊 Smooth drawing motion – The app features smooth stroke rendering with easing effects.
  • πŸ’‘ No installation required – Just open it in your browser and start drawing instantly!

πŸ› οΈ Tech Stack

  • HTML, CSS, JavaScript: For the core functionality and layout.
  • TensorFlow.js: For real-time hand gesture recognition and tracking.
  • MediaPipe Hands: Provides hand landmark detection and tracking.
  • Canvas API: Renders strokes and manages the drawing surface.

πŸ“‚ Project Structure-

Here’s a breakdown of the project structure:

πŸ“ AI-powered-Hand-gesture-whiteboard/
β”œβ”€β”€ index.html        # Main HTML layout
β”œβ”€β”€ styles.css        # Simple UI styling
└── script.js         # Logic for drawing & gesture recognition using MediaPipe

πŸ“Έ How It Works
Launch the app: Open the app in your browser and allow webcam access.

Track hand movements: The app tracks your index finger tip (landmark 8) using MediaPipe.

Draw or erase: As you move your finger, it draws on the canvas. Switch to "Eraser" mode to clear the canvas.

Smooth experience: The drawing is smooth, thanks to real-time hand tracking and motion easing.

πŸ§ͺ Run Locally
To run the app on your local machine, follow these steps:

Clone the repository:

bash
Copy
Edit
git clone https://github.com/CuriousCoder25/AI-powered-Hand-gesture-whiteboard.git
Navigate to the project directory:

bash
Copy
Edit
cd AI-powered-Hand-gesture-whiteboard
Open index.html in your browser (you can use a local server like Live Server in VS Code for a smoother experience).

Allow webcam access: Make sure your webcam is enabled and the browser prompts you for camera permissions.

⚠️ Prerequisites
Webcam for hand tracking.

A modern browser (Chrome, Firefox, etc.) with WebRTC support.

πŸ™ Acknowledgements
This project utilizes the following technologies:

MediaPipe Hands for hand landmark detection.

TensorFlow.js for machine learning and gesture recognition.

JSDelivr CDN for serving external libraries.

πŸͺΆ License
This project is licensed under the MIT License. Feel free to fork, remix, or contribute to the code.

πŸ•ŠοΈ Outro
A canvas of code, drawn by a free soul – CuriousCoder25. 🎨
Now, go ahead, let your creativity flow!

About

AI whiteboard web app using hand gesture input via TensorFlow.js and MediaPipe

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors