Robust Hand Gesture Recognition with Feature Selection and Hierarchical Temporal Self-Similarities

• DOI: 10.7763/ijiee.2013.v3.368
• Publication Date: 2013-04-12T03:54:56Z
• Authors: Yuhang Wu; Liangke Zhao; Hui Ding
• Keywords: Feature (linguistics)

There are increasing numbers of hand interaction system based on Microsoft Kinect for its providing the extra depth information which facilitates segmentation. However, most recent papers focus stable recognition whose assumption can hardly be fulfilled in highly interactive HCI environment. We proposed a robust method to recognize both moving and hand. explored several features RGB images novel descriptor, then built feature selection model find recognition. Then, we exploited hierarchical self-similarity matrix (H-SSM) detect gesture transformation further enhancing robustness. Our widely used effectiveness has been verified through experiment.