Real-Time and Continuous Hand Gesture Spotting: an Approach Based on Artificial Neural Networks

TL;DR

This paper presents a real-time, continuous hand gesture spotting system using a dual-ANN architecture with a data glove, achieving high recognition accuracy for industrial robot control.

Contribution

It introduces a novel dual-ANN architecture for simultaneous gesture segmentation and recognition in continuous, real-time scenarios.

Findings

Over 99% recognition accuracy for 10 gestures

Over 96% recognition accuracy for 30 gestures

Low training and learning time

Abstract

New and more natural human-robot interfaces are of crucial interest to the evolution of robotics. This paper addresses continuous and real-time hand gesture spotting, i.e., gesture segmentation plus gesture recognition. Gesture patterns are recognized by using artificial neural networks (ANNs) specifically adapted to the process of controlling an industrial robot. Since in continuous gesture recognition the communicative gestures appear intermittently with the noncommunicative, we are proposing a new architecture with two ANNs in series to recognize both kinds of gesture. A data glove is used as interface technology. Experimental results demonstrated that the proposed solution presents high recognition rates (over 99% for a library of ten gestures and over 96% for a library of thirty gestures), low training and learning time and a good capacity to generalize from particular situations.