Indian Sign Language Gesture Recognition Using Deep Convolutional Neural Network

Abstract

Communication is extremely important in ones life and the most widely used type of communication is verbal communication. But there are people with hearing and speech impairment who cannot communicate verbally and the language which they use for communication is sign language. And in India, the Indian Sign Language (ISL) is used. These languages are visual language which uses a variety of visual signs or gestures. The majority of the people are not aware of the semantics of these gesture and this creates a communication gap between both the community. So there is a need for an automatic system. There has been a lot of research done in the field of American Sign language but unfortunately not in the case of ISL. This is due to lack of standard dataset and the variation in the language. The aim of this work is to recognize ISL gestures and convert it into text. Currently, an image recognition model was implemented using deep CNN (Inception V3 model) which accepts input image and it is passed through a series of layers and the output is generated. We have achieved an accuracy of 93%.