Feature fusion for 3D hand gesture recognition by learning a shared hidden space》.pdf

Pattern Recognition Letters 33 (2012) 476–484 Contents lists available at ScienceDirect Pattern Recognition Letters journal homepage: www.else /locate/patrec Feature fusion for 3D hand gesture recognition by learning a shared hidden space Jun Cheng a,⇑, Can Xie a,b, Wei Bian a,b,c, Dacheng Tao c a Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China b The Chinese University of Hong Kong c Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology, Sydney Broadway NSW 2007, Australia a r t i c l e i n f o a b s t r a c t Article history: Hand gesture recognition has been intensively applied in various human–computer interaction (HCI) sys- Available online 29 December 2010 tems. Different hand gesture recognition methods were developed based on particular features, e.g., ges- ture trajectories and acceleration signals. However, it has been noticed that the limitation of either Keywords: features can lead to flaws of a HCI system. In this paper, to overcome the limitations but combine the Hand gesture recognition merits of both features, we propose a novel feature fusion approach for 3D hand gesture recognition. Feature fusion In our approach, gesture trajectories are represented by the intersection numbers with randomly gener- Shared hidden space ated line segments on their 2D princ