Research on Dynamic Gesture Recognition Algorithm Based on Multi-touch Human-computer Interaction Devices in Classroom Teaching

DOI

10.2991/icmmita-16.2016.232How to use a DOI?

Keywords

Human-computer Interaction; Dynamic Gesture Recognition; Education Cloud Integration Platform of starC

Abstract

In this paper, we propose a dynamic gesture recognition approach based on multi-touch devices. This method contains three stages: dynamic gesture stroke collection, gesture feature extraction, gesture analysis and recognition. In order to recognize nine kinds of gestures in classroom interaction process, a point packet model with fault tolerance is proposed by applying convex of the gesture stroke, track length width ratio, geometric feature ratio and Freeman chain code information. Furthermore, this method combines the number of track points and fuzzy pattern recognition method, establishes the membership function of fuzzy set, and find out the fuzzy similarity relationship of gesture recognition. The experiments show that gesture recognition rate reaches 93% to recognize nine different dynamic gestures.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhao Zhang
AU  - Xiuling He
AU  - Zengzhao Chen
AU  - Ke Wu
PY  - 2017/01
DA  - 2017/01
TI  - Research on Dynamic Gesture Recognition Algorithm Based on Multi-touch Human-computer Interaction Devices in Classroom Teaching
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.232
DO  - 10.2991/icmmita-16.2016.232
ID  - Zhang2017/01
ER  -