Real-Time Detection of Sign Language using Deep Learning

Abstract

Sign language is one of the more experienced and regular types of correspondence language, however, since most are unfamiliar with sign communication and interpreters are undeniably challenging to stop by we have concocted a constant technique that uses neural organization for fingerspelling based American gesture-based communication. It is a profoundly visual-spatial, semantically complete language. It is typically the first language and the main means of communication for deaf individuals. Sign Language is communication that relies on hand signs, gestures, and expressions, generally used in the deaf community. But people outside of the deaf community find it hard or almost impossible to speak with deaf people. They need to rely on an interpreter which may both be expensive and hurt the privacy of the people trying to communicate. This paper proposes a method that makes use of a Convolutional Neural Network to identify and recognize hand signs which are captured in real-time through a webcam. Since there is no universal sign language. The model was specifically trained on American Sign Language alphabets.