Sign Language Gesture Recognition

Abstract

Recognition of Sign Language is one of the rising areas of research now days. Invention of first data glove made this field a topic of research. The basic concept of this project is to use computing technology to enable communication between two people who cannot converse directly. One person using sign language while the other unable to understand it needs something in between which can perform translation between the two different modes of communication they know. This project intends to assist the person using sign language in communicating with those who cannot understand sign language. The concept is to minimize this communication gap using a system which outputs the conversation as text & audio output. With the advancement of science and technology many techniques have been developed not only to minimize the problem of deaf people but also to implement it in different fields. Many research works related to Sign languages have been done as for example the American Sign Language, the British Sign Language, Japanese Sign Language etc. It is the need of the time to introduce such a system that not only reduce the communication breach between deaf and normal community but also is a mean of bringing deaf community to the normal world. The developed algorithm converts sign language signals collected by a 5 DT data glove and Nintendo power Glove data into text & audio output. The data has been processed by different classifiers and the results have been compared within the various classifiers and existing techniques to highlight the optimum methodology.