Dynamic fingure gesture recognition using KINECT

Abstract

Sign language is the only means of communication for hearing and speech impaired people to communicate with other normal people. Gesture recognizing devices and algorithms have been developed to make this communication easy but not with the desired accuracy and speed. Hence they cannot be deployed in real time environments such as auditoriums and classrooms. Dynamic gesture recognition is one way to subdue the issue. For now static gesture recognition employs both hands n fingers but dynamic gesture recognition is limited to hands alone. Since most of the gestures are shown using fingers, a dynamic finger gesture recognition system that utilizes microsoft kinect which enables real-time user interaction through its RGB camera and depth sensor is proposed.