Interaction and control with the auxiliary of hand gesture

Abstract

This paper presents method used hand gesture recognition in human-computer interaction and control. Nowadays in dataglove-driven motion capture field, researchers preprocess the raw sensor data of the glove with calibration methods for acquiring a high precision in the VR environment. But there are still alternative solutions. Some machine learning algorithms, for example the self-organizing map method, offer a powerful capacity in the case of hand gesture recognition with uncalibrated glove data. We present the reason we introduced the SOM into the recognition process and how it works. Our goal is to construct a stable and robust mechanism to recognize hand gesture and then put it into hand gesture control system as an interaction platform for virtual reality.