Recognition of alphabets of Indian sign language by sugeno type fuzzy neural network

Abstract

Sign Language Recognition has evolved as an important area of research in the past few years. Sign language can be defined as the language of the deaf and dumb people by which they are able to express their thoughts. Such people are not able to use acoustic means for the purpose of communicating, instead they convey message by making use of the Sign Language. Thus Sign language is a means developed for the deaf and dumb society by which they can visually transmit different sign patterns to convey their message by combining simultaneously hand shapes, movement of hands and orientation of hands which are also sometimes associated with the facial expressions. Like all other languages, Sign Languages also have their own alphabets and grammar. As these sign languages are not much known to the people outside the deaf and dumb communities and thus there always exists a gap between the impaired people and the normal people who have the abilities to talk and listen. The techniques developed for recognizing signs would allow the creation of systems which can help to eliminate this barrier, by providing computer tools to assist in the learning of sign language and in creating a system to translate the sign language to text for understanding of normal people. This would help a hearing impaired person to easily interact with a normal person at different levels in the society. Sign Languages are not same throughout the world. These are different for different parts of the world. The Sign Language used in India is called as the Indian Sign Language. In this paper we attempt to summarize the significance of features associated with the alphabets of the Indian Sign Language.