Automatic sign language recognition: A survey

Abstract

Sign Language, which is a fully visual language with its own grammar, differs largely from that of spoken languages [21]. After nearly 30 years of research, SL recognition still in its infancy when compared to Automatic Speech Recognition. When producing Sign language (SL), different body parts are involved. Most importantly the hands, but also facial expressions and body movements/postures. The recognition of SL is still one of the most challenging problems in gesture recognition. In this survey, we are going to discuss the advancement of sign language recognition through the last decade. In this paper, we provide a review of the state-of-the-art building blocks of Automatic Sign Language Recognition (ASLR) system, from feature extraction up to sign.