This project uses TensorFlow.js/ML5.js to detect the pose of a human hand in real-time. The model is trained to recognize a variety of hand poses, including open, closed, and partially open.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
Before you can run this project, you will need to have the following software installed:
Node.js
p5.js
ml5.js
All the dependencies can be found in the scripts folder.
Open index.html file and wait for the model to load.
After the model is loaded,you can press S key on the keyboard to start the model.This will start the model and begin detecting hand poses in real-time.
And press the X key on the keyboard to stop the model.
You can use gestures to control the page,
Turn your hand to right and hold for few seconds.
Turn your hand to left,until your thumb points in the downward direction and hold for few seconds.
You should see the page scroll up/down according tou your hand gestures. To stop the model press the X key on the keyboard.
This is a simplified version of the above model built on the Web Browser(p5.js).
TensorFlow.js : A JavaScript library for training and deploying machine learning models in the browser.
p5.js : A JavaScript library for creative coding, with a focus on making coding accessible and inclusive for artists, designers, educators, beginners
ml5.js : A Javascript library for easy accesiblity of machine learning models build on top of Tensorflow.js.
A_V_Aniketh : GitHub Account
This project is licensed under the Apache 2.0 License - see the LICENSE.md file for details.
TensorFlow.js_Handpose_Example : This project was inspired by the TensorFlow.js Handpose Example.