Visual Methods for Sign Language Recognition: A Modality-Based Review

Sign language visual recognition from continuous multi-modal streams is still one of the most challenging fields. Recent advances in human actions are exploiting ascension GPU-based learning massive data, and getting closer to human-like performances. They then prone creating interactive services for deaf hearing-impaired communities. A population that expected grow considerably years come. This chapter aims at reviewing literature with sign-language understanding as a scope. The methods analyzed will be mainly organized according different types unimodal inputs exploited, their relative combinations pipeline steps. In each section, we detail compare related datasets, approaches distinguish open contribution paths suitable creation sign services. Special attention paid commercial solutions handling facial expressions signing.