Hand Gesture Recognition System Based on a Geometric Model and Rule Based Classifier

Abstract

As a part of natural interfaces the sign language recognition (SLR) is considered an important area of research. Such systems are considered useful tools for assisting the deaf. For example, one of the applications of sign language recognition is transcribing notes and saving sign language presentations into digital format. Hand gesture recognition systems can also be used to control useful machines, computers, screen pointers or camera-based selection devices, like the kind used on modern ‘Smart TVs’ or console games that use the Microsoft Xbox Kinect camera. A great deal of research has been paid for this area but few ones handled the Arabic Sign Language (ArSL). This work describes an isolated SLR system that extracts geometric features from a camera for the hand gesture and builds a geometric model for the hand gesture. The rule based classifier was then used for the recognition process based on the determined geometric features of a specific gesture. The proposed model was tested on seven ArSL words. The overall recognition rate was about 95.3%.