A gesture recogintion architecture for Arabic sign language communication system

Abstract

Sign language is the most natural and expressive way for the hearing impaired to communicate. With technological advances in multimedia systems and applications, technology-mediated sign language communication systems have long attracted researchers to enhance the communication capabilities for the speech and hearing impaired, promising improved social opportunities and integration. This paper introduces a framework for Arabic sign language communication using Microsoft Kinect device. The merit of the proposed framework is twofold: first, the framework supports an affordable and easily deployable real-time communication system using Arabic sign language, and secondly, it provides a real-time feedback about the signer performance via real-time avatar animation. A prototype application is developed to demonstrate the merits of the proposed framework. Experimental results show that the proposed Arabic sign language method enjoys a sign detection rate of 96 %. Furthermore, the average task completion time to complete an Arabic sign was about 2.2 s. This implies that the proposed method can be used to create a real-time Arabic sign language communication system. Finally, participants of the study highlighted that the proposed system is user-friendly and easy to use, and can be used at low cost to recognize and display Arabic signs.