Hand Tracking by using Python and Machine Learning

Abstract

Hand tracking is an important component in most practical gesture interaction. In this work, we present a real-time method for hand gesture recognition. We present another constant hand global positioning framework dependent on a solitary profundity camera. In our Project, the hand region is extracted from the background with the background removing method. Then, the palm and fingers are segmented so as to detect and recognize the fingers. In this paper, an automatic hand tracking and segmentation method based on depth information is proposed. Hand depth is determined and then exact hand region is obtained. In this manner, exact hand tracking is realized with very less time and regardless of the complex background. From the tracking process we extract several hand features that are fed to a finite state classifier which identifies the hand configuration. Experiments show the effectiveness of the hand tracking and dynamic gesture recognition. A research was based on a number of algorithms that could best explained a hand gesture. In the pre-processing state, a selfdeveloped algorithm eliminate the background of each training gesture. After that the image is transform into a binary image and the sums of all diagonal segments of the pictures are taken. A completely powerful hand gesture recognition system is still under development.