Automatic Hand Gesture Recognition Based on Shape Context
In this paper, we propose a novel method for automatic hand gesture recognition from images based on shape context. Unlike conventional approaches, our method can robustly detect hand gestures rotated with arbitrary angle. Specifically, we improve the exi
- PDF / 680,809 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 34 Downloads / 248 Views
Abstract In this paper, we propose a novel method for automatic hand gesture recognition from images based on shape context. Unlike conventional approaches, our method can robustly detect hand gestures rotated with arbitrary angle. Specifically, we improve the existing shape context to rotational invariant by creating a new log-polar space based on the tangent line of the boundary points. We first align the two hand gestures by solving a correspondence problem. The similarity of two hand gestures are obtained by calculating the shape distance based on our proposed rotational invariant shape context. Finally, the best matched result is identified by retrieving the gesture with the maximal shape similarity. Our method is evaluated using a standard simulated gesture dataset. Experimental results show that our method can accurately identify hand gestures, either with or without rotation. Comparison experiments also suggest that our method outperforms existing hand gesture recognition methods based on conventional shape context. Keywords Shape context Gesture recognition
Rotational invariance The corresponding problem
1 Introduction Due to its wide applications in computer vision and pattern recognitions, automatic hand gesture recognition becomes a more and more popular research topic. With the development of computer vision, more and more researchers have been involved in this promising problem. For example, automatic hand gesture recognition can help us to communicate with deaf people. It can also improve our H. Wu (&) L. Wang M. Song Z. Wen College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China e-mail: [email protected]
Z. Wen and T. Li (eds.), Foundations of Intelligent Systems, Advances in Intelligent Systems and Computing 277, DOI: 10.1007/978-3-642-54924-3_83, Springer-Verlag Berlin Heidelberg 2014
889
890
H. Wu et al.
personal experience in the 3D game, in intelligent transportation system or automatic driving motors and so on. Therefore, automatic gesture detection becomes extremely important in the field of computer vision and has a variety of promising practical applications. Recently, researchers have developed a number of novel technologies for automatically detecting hand gestures, such as the technologies based on the skin color [1], shape similarity [2] and so on. Although a certain extent improvements have been achieved for the above hand gesture recognition technologies, they still have several limitations, including sensitive to the influence of lighting, excessive dependence on the hardware facilities and limited types of hand gesture recognition. To solve the above problems, more sophisticated solutions should be elaborated. In this paper, we propose a novel automatic hand gesture recognition method. Based on a rotational invariant shape context, our method is much more robust and stable under different lighting conditions. More importantly, without any dependence on hardware facilities, our method still achieves a stable performance. In addi
Data Loading...
