Towards Computer-Aided Sign Language Recognition Technique: A Directional Review

For the hearing and speech impaired, Sign Language (SL) is their main communication tool. To enable them communicate smoothly with those who don't understand SL, it is necessary to translate SL into text or speech through recognition. We review the research status and progress in the field of SL recognition, based on the analysis of off-the-shelf SL translation methods and systems. This paper describes a number of recognition methods, and they are divided into data glove-based and vision-based approaches according to the motion capture device; In addition, vision-based approaches are categorized into color-based and depth-based techniques by the used camera. Moreover, this paper critically discusses current SL recognition technology, and points out the problems and challenges, so as to provide guideline for future work.