Hand Gesture Control

GitHub DrDEXT3R/HandGestureControl


It is a program that recognizes hand gestures shown to the webcam. Each frame is subjected to the process of creating a hand mask, which is then given as the input of a learned neural network to predict result. Therefore, it is possible to control the video player by perform the appropriate gestures.

Demo 1 Demo 2 Masks
The gallery showing how the application works.
Hand gesture recognition (1); controlling video player (2); hand masks generated in various conditions (3)

Built With

  • Python 3 - The programming language
  • TensorFlow - A end-to-end open source platform for machine learning
  • Keras - A high-level neural networks API written in Python
  • OpenCV - Computer vision and machine learning software library
  • NumPy - The package for scientific computing with Python
  • OpenBLAS - An optimized BLAS library (Basic Linear Algebra Subprogram)
  • pynput - This library allows control and monitor input devices
  • h5py - The package is a Pythonic interface to the HDF5 binary data format
  • os - This module provides a portable way of using operating system dependent functionality


This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.