A systematic literature review on vision-based hand gesture for sign language translation

Abstract

Deaf and hard of hearing people use sign language to communicate. People around mute and deaf people have difficulty communicating with each other if they do not understand sign language. This problem has prompted many researchers to conduct studies on sign language translation. However, there is a lack of compilation of SLR on this topic. Therefore, this paper aims to provide a thorough literature review of previous studies on sign language to text translation based on the vision method. PRISMA (Preferred Reporting Items to writing a standard Systematic Review and Meta-Analyses) is used in this systematic review. Two primary databases, Web of Science and Scopus, have been used to search for relevant articles and resources included in this systematic literature review. Based on the outcome of the systematic review of the topic, the primary studies on sign language translation systems were conducted using self-generated datasets more than public datasets. More static action sign language was studied compared to dynamic action sign language. For the type of recognition, more alphabet sign language was studied compared to digit, word, or sentence sign language. Other than that, most studies used digital cameras rather than Microsoft Kinect or a webcam. The most used classification method was Convolution Neural Network (CNN). The study is intended to guide readers and researchers for future research and knowledge enhancement in the field of sign language recognition.