A Brief Review of Sign Language Recognition Methods and Cutting-edge Technologies

Sign Language Recognition (SLR) has acquired a considerable amount of attentions in recent years and attracted widespread interests. Sign language recognition methods have continuously evolved from traditional artificial neural networks to deep learning methods, and these methods have led to increasing accuracy in sign language recognition. Advances in sign language recognition technology have provided the deaf community with a broader communication space, while also injecting new vitality into the technology field. The majority of widely used sign language recognition methods are derived from neural networks and deep learning models, such as convolutional neural networks, recurrent neural networks and long and short-term memory networks. In recent years, the rapidly developing BEiT model is expected to be used in the realm of sign language recognition, so that it can develop more intelligent and efficient applications in the future, and make more important contributions to the barrier-free communication and exchange in the society. The aim of this paper is to summarize the methods applied in the field of sign language recognition and the cutting-edge technologies in sign language recognition.