A dynamic gesture recognition method based on computer vision

In recent years, the development of human-computer interaction (HCI) techniques is very fast and the typical application is the gesture interaction technology. This paper proposes a useful and robust dynamic gesture recognition method. The first step is to detect hand in every image frame obtained from a USB camera, through skin segmentation and hand feature extraction. Hand region is segmented based on YCrCb color space and detected by detecting the number of fingers. Then, the algorithm based on ellipse fitting and motion feature is used to track hand. We recognize the trajectory of hand obtained after tracking based on a simple method. The experimental results show that the proposed method is reliable and robust.