Static hand gesture recognition (SHGR) from visual images has a number of potential applications in human-computer interaction (HCI), machine vision, virtual reality (VR), and machine control, etc., in industrial and academic area. Most conventional approaches of SHGR have employed data gloves or others auxiliary equipment. For more natural and intuitive interface, SHGR should be recognized from
... [Show full abstract] visual images as the communication between human beings and computer without using any external device. In this paper, we focus on addressing the problem of high dexterity of hand and self-occlusions created in the limited view of the camera or illumination variations, a novel SHGR method was proposed to explicitly utilize depth information by using 3-D point cloud. First, “hand image” is segmented by a set of depth threshold. Next, hand image normalization will be performed to ensure that the extracted feature descriptors are scale and rotation invariant. Third, by robustly coding and pooling 3-D facets, the proposed descriptor can effectively represent the various hand postures. After that, SVM with linear kernel function is used to address the issue of posture recognition. Experimental results based on posture dataset captured by Kinect sensor (from 1 to 10) demonstrate the effectiveness of the proposed approach and the average recognition rate of our method is over 94%.