Two-way Sign Language Interpreter

Abstract

A sign language translator is an important milestones in facilitating communication between the deaf community and the public. Sign language has a remarkable advancement that has grown over the past years. Unfortunately, there are some drawbacks that have come along with this language. Not everyone knows how to interpret a sign language when having a conversation with a deaf and dumb person. There is always a need to communicate using sign language. One finds it hard to communicate without an interpreter. To solve this, we need a product that is versatile and robust. We need to convert the sign language so that it is understood by common people and will help them to communicate without any barriers. .We hereby present the development and implementation of an Indian Sign Language (ISL) fingerspelling translator based on a convolutional neural network. We will divide our implementation in Two modules. The first module will handle the user input which will be taken by device Camera. Now the second module contains the pre-processing of the input images, the different sign of images will be identified with the help of CNN and then internally ANN will be applied on the processed image. The identified signed of image will be then compared with the Thousands of gesture data set stored and their associated output, which are already stored. Corresponding word will be shown to User. In the same way if User will give voice input then corresponding gesture will be shown to User. The main purpose of this project is to eliminate the barrier between the deaf and dumb and the rest.