Automatic static hand gesture recognition using ToF cameras

This paper presents an automatic algorithm for static hand gesture recognition relying on both depth and intensity information provided by a time-of-flight (ToF) camera. The combined depth and intensity information facilitates the segmentation process, even in the presence of a cluttered background (2 misses out of 450 images). Gesture classification is based on a decision tree using structural descriptions of partitioned contour segments. Classification was tested on 9 different gestures. The final mean recognition rate is satisfactory, of about 93.3%.

[1]  Bian Wu,et al.  A hand gesture recognition system based on local linear embedding , 2005, J. Vis. Lang. Comput..

[2]  Tin Hninn Hninn Maung,et al.  Real-Time Hand Tracking and Gesture Recognition System Using Neural Networks , 2009 .

[3]  Shuzhi Sam Ge,et al.  Hand Gesture Recognition and Tracking based on Distributed Locally Linear Embedding , 2006, 2006 IEEE Conference on Robotics, Automation and Mechatronics.

[4]  Michael G. Strintzis,et al.  Real-time hand posture recognition using range data , 2008, Image Vis. Comput..

[5]  Zhi Li,et al.  Real time Hand Gesture Recognition using a Range Camera , 2009, ICRA 2009.

[6]  Liu Yun,et al.  A Hand Gesture Recognition Method Based on Multi-Feature Fusion and Template Matching , 2012 .

[7]  Agnès Just,et al.  A comparative study of two state-of-the-art sequence processing techniques for hand gesture recognition , 2009, Comput. Vis. Image Underst..

[8]  Liviu Goras,et al.  On HMM static hand gesture recognition , 2011, ISSCS 2011 - International Symposium on Signals, Circuits and Systems.

[9]  Haiying Guan Vision-based 3D hand posture estimation using hierarchical-ISOSOM , 2007 .

[10]  Christoph Rasche,et al.  An Approach to the Parameterization of Structure for Fast Categorization , 2010, International Journal of Computer Vision.

[11]  S. Mitra,et al.  Gesture Recognition: A Survey , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).