Hand gesture to speech conversion using Matlab

Abstract

Hand gesture is one of the typical methods used in sign language for non-verbal communication. Sign gestures are a non-verbal visual language, different from the spoken language, but serving the same function. It is often very difficult for the hearing impaired community to communicate their ideas and creativity to the normal humans. This paper presents a system that will not only automatically recognize the hand gestures but also convert it into corresponding speech output so that speaking impaired person can easily communicate with normal people. The gesture to speech system, G2S, has been developed using the skin colour segmentation. The system consists of camera attached to computer that will take images of hand gestures. Image segmentation & feature extraction algorithm is used to recognize the hand gestures of the signer. According to recognized hand gestures, corresponding pre-recorded sound track will be played.