Real Time Sign Language Recognition and Speech Generation

Abstract

Sign Language is the method of communication of deaf and dumb people all over the world. However, it has always been a difficulty in communication between a verbal impaired person and a normal person. Sign Language Recognition is a breakthrough for helping deaf-mute people to communicate with others. The commercialization of an economical and accurate recognition system is today’s concern of researchers all over the world. Thus, sign language recognition systems based on Image processing and neural networks are preferred over gadget system as they are more accurate and easier to make. The aim of this paper is to build a user friendly and accurate sign language recognition system trained by neural network thereby generating text and speech of the input gesture. This paper also presents text to sign language generation model that enables a way to establish a two-way communication without the need of a translator.