A Survey: The Sensor-Based Method for Sign Language Recognition

Sign language is a crucial communication carrier among deaf people to express and exchange their thoughts and emotions. However, ordinary individuals cannot acquire proficiency in sign language in the short term, which leads to deaf people facing huge barriers with the sound community. Regarding this conundrum, it is valuable to investigate Sign Language Recognition (SLR) equipped with sensors which collect data for the following computer vision processing. This study has reviewed the sensor-based SLR methods, which can transform heterogeneous signals from various underlying sensors into high-level motion representations. Specifically, we have summarized current developments in sensor-based SLR techniques from the perspective of modalities. Addtionally, we have also distilled the sensor-based SLR paradigm and compared the state-of-the-art works, including computer vision. Following that, we have concluded the research opportunities and future work expectations.