ABSTRACT
Sign language, being the basic means of communication between speciallyabled people, that is, deaf, and normal ones, a massive amount of research works has been carried out in this field. However, since sign language varies from country to country and region to region, and also most of the people do not have enough knowledge about this medium of communication, it is extremely difficult to build a robust and efficient system that can solve sign language recognition (SLR) problems. Some sign languages for which active research has been done are Indian Sign Language, American Sign Language, British Sign Language, etc. However, when we talk about Nepali Sign Language (NSL), the research work is extremely limited. In this chapter, we review different vision-based as well as sensor-based models of NSL recognition using different approaches that were published from 2015 to 2019. Among different techniques, vision-based approaches along with deep learning algorithms were mostly used. Classification algorithms included: Convolutional Neural Network, Random Forest Algorithm, K-Nearest
