Title: Online hand gesture recognition using enhanced $N recogniser based on a depth camera
Authors: Kisang Kim; Hyung-Il Choi
Addresses: School of Media, Soongsil University, Seoul, Korea ' School of Media, Soongsil University, Seoul, Korea
Abstract: In this paper, we propose a hand gesture recognition system using a depth camera for user notes correction. For this system, we developed a gesture recognition and hand tracking method. In tracking, we focus on the index finger tip point. To extract the point, we detect the hand region using depth information and determine the top point of the region. For recognition, we use the $N recogniser. However, the recogniser has a problem that it is too insensitive in rotation. Therefore, we propose an enhanced $N recogniser. We include the process of matching the angle between the starting gesture pose and the ending gesture pose. Through experimental results, we show that the performance improves with our methods.
Keywords: hand gesture recognition; $N recogniser; hand tracking; depth camera; user notes correction; index finger tip point; gesture pose; rotation.
DOI: 10.1504/IJCVR.2016.077352
International Journal of Computational Vision and Robotics, 2016 Vol.6 No.3, pp.214 - 222
Received: 27 Jul 2014
Accepted: 26 Dec 2014
Published online: 29 Jun 2016 *