SOM-based hand gesture recognition for virtual interactions

Abstract

In nowadays, hand gestures can be used as a more natural and convenient way for human computer interaction. The direct interface of hand gestures provides us a new way for communicating with the virtual environment. In this paper, we propose a new hand gesture recognition method using self-organizing map (SOM) with datagloves. The SOM method is a type of machine learning algorithm. It deals with the raw data sampled from datagloves as input vectors, and builds a mapping between these uncalibrated data and gesture commands. The results show the average recognition rate and time efficiency when using SOM for dataglove-based hand gesture recognition. A series of tasks in virtual house illustrate the performance of our interaction method based on hand gesture recognition.