Kinect Based Dynamic Hand Gesture Recognition Algorithm Research

Abstract

In dynamic gesture track recognition, gesture recognition rate has always been a problem, Because the traditional hand gesture recognition in how to separate the hand type from the surrounding environment, and then determine the palm position has been one of the difficult problems. This paper presents a Kinect based dynamic gesture trajectory identification method, use OpenNI where palm is defined as a Kinect node, quickly and accurately get the palm position coordinates, and then use the HMM technology to do gesture model training to improve the recognition rate. The experimental results show that this method of gesture track recognition rate is higher than the traditional.