期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2014
卷号：14
期号：2
页码：149-155
出版社：International Journal of Computer Science and Network Security
摘要：The increasing ubiquity of today's Smartphones made them an ideal platform for many emerging mobile applications that range from navigation systems to healthcare monitoring. However, the majority of the mobile systems are being marketed primarily to the able-bodied users and most of them fail to be accessible to people with disabilities especially the deaf. As a way of enabling the deaf to interact naturally with the Smartphones, automatic hand sign recognition appears as a suitable means. In this paper, we propose, AndroSpell, vision-based Smartphones software to automatically recognize Arabic Fingerspelling signs. The system prototype was built entirely on the top of the cameraphone and was able to classify up to 10 postures with accuracy of 97%. The implementation and the evaluation of the system provide clear evidence that the emerging capabilities of the cameraphones could be fairly harnessed for use as an accessible technology for the deaf.
关键词：mobile accessibility; mobile computing; posture recognition
