基于深度信息的实时手势识别和虚拟书写系统.pdf

Computer Engineering and Applications   HUANG Xiaolin, DONG Hongwei 214122 College of Internet of Things, Jiangnan University, Wuxi, Jiangshu, 214122, China Depth-based real-time hand gesture recognition and virtual writing systems. Computer Engineering and Applications Abstract: Inspired by the successful application of the contactless somatosensory interaction technology in the field of human-computer interaction, this paper presents a real-time Kinect depth camera based contactless virtual hand writing technique. In our technique, hand regions are first detected and segmented utilizing both color and depth information. Then hand fingers are rapidly recognized using a modified scan conversion method of a circle in order to recognize different hand gestures. Finally, using tracking by detection of a fingertip to obtain the fingertip trajectory and segment out individual trajectories for English and Chinese characters. Further a random forests algorithm is used to identify the correct characters from these individual trajectories. This depth information based hand gesture recognition and virtual hand writing technique can overcome the effects of light and color overlap and make the real-time detection and identification of gestures and hand writing more robust and reliable. The recognition accuracy can arrive at 93.25% and the speed of the recognition is about 25fps. Key words: depth image, hand gesture recognition, hand writing recognition, random forests doi:10.37