Description

Hand gesture recognition is of great importance for human-computer interaction (HCI), because of its extensive applications in virtual reality, sign language recognition, and computer games. Many hand gesture recognition methods are based on the body of work related to body pose estimation. The state-of-the-art of body estimation techniques began to make use of depth sensors to track human body parts. In this project the system proposed a new hand motion capture procedure for establishing the real gesture data set. This model contains not only gesture descriptors but also the 3-D position of the hand. In the demonstration application, the system show how they are used for recognizing dynamic gestures.