Designing a sign language translation system using kinect motion sensor device

摘要

Hand gesture is one of the most natural and expressive ways for the hearing impaired. However, because of the complexity of dynamic gestures either static gestures, postures, or a small set of dynamic gestures are focused by most researchers. In this paper, Kinect Motion Sensor Device is used to recognize the gesture of the user. But the gesture of each user of a particular word will be slightly different. As real-time recognition of a large set of dynamic gestures is considered, some efficient algorithms and models are needed. Here an efficient algorithm is used to recognize the gesture and translate them. In this paper, in order to recognize the gesture in both training and translation mode a grid view algorithm has been used. We evaluated our system by translating gesture by various people for twelve different words and experimental results reveals that our proposed system has about eighty percent success rate in translating gestures.