Gesture Recognition Using Kinect for Sign Language Translation

Sign Language is a widely used method of communication among the community of deaf-mute people. It contains some series of body gestures, which enables a person to interact without the need of spoken words. Although the use of sign language is very popular among the deaf-mute people but the other communities don't even try to learn it, this creates a gulf of communication and hence becomes a cause of the isolation of physically impaired people. The problem creates a requirement of a system which can facilitate a way of communication between these two communities. This paper presents a novel method for identification of an isolated sign language gesture using Microsoft Kinect. This paper presents the way of extracting some highly robust features from the depth image provided by Kinect and to use them in creating a robust and accurate gesture recognition system, for the purpose of sign language translation. Apart from translation, the proposed system also opens the doors of endless applications in the field of Human Computer Interaction. The proposed algorithm helps in translating a sign language gesture performed by a user, which in-turn can be used as an input for different types of applications.