Static Gesture Recognition Based on RGB-D Depth Information

Abstract:

This paper presents a method of static gesture recognition based on RGB-D depth image technology for problems of static gesture recognition under complex background.First,Microsoft's Kincet camera is for data collection.The hand region is extracted from complex background via depth image. Then appearance features are integrated to build the decision tree model which based on hands and largest index angle of the fingertips for hand gesture recognition.Nine common gestures with complex background were tested in the system.Experiments show that the method can implement efficiently,and has a strong robustness.

• Periodical: Applied Mechanics and Materials (Volume 667)
• Pages: 248-254
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.667.248
• Online since: October 2014
• Authors: Yi Wang*, Xiu Cheng Dong, Chang Long Li, Xi Mu Yu
• Keywords: Appearance Gesture Feature, Decision Tree, RGB-D, Static Gesture Recognition

References

[1] Lee Jaemin, Hironori Takimoto, Hitoshi Yamauchi. A Robust Gesture Recognition based on Depth Data The 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision. [S. 1. ]: [s. n], pp.127-131, (2013).

DOI: 10.1109/fcv.2013.6485474

[2] Haitham Hasan, S. Abdul Kareem. Human Computer Interaction for Vision Based Hand Gesture Recognition: A Survey. International Conference on Advanced Computer Science Applications and Technologies. [S. 1. ]: IEEE Press, pp.55-60, 2013.

DOI: 10.1109/acsat.2012.37

[3] Jesus Suarez, Robin R. Murphy. Hand Gesture Recognition with Depth Images: A Review. The 21st IEEE International Symposium on Robot and Human Interactive Communication. [S. 1. ]: [s. n], pp.411-417, (2012).

DOI: 10.1109/roman.2012.6343787

[4] B. D. Zarit, B. J. Super and F. K. H. Quek. Comparison of five color models in skin pixel classification. Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, 1999. Proceedings. International Workshop on, pp.58-63, (1999).

DOI: 10.1109/ratfg.1999.799224

[5] Guillaume Doisy, Verena Vanessa Hafner, Position-Invariant. Real-Time Gesture Recognition Based on Dynamic Time Warping. Proc. of HRI 2013 Proceedings. [S. 1. ]: IEEE Press, pp.87-88, (2013).

DOI: 10.1109/hri.2013.6483514

[6] Valentino Frati, Domenico Prattichizzo. Using Kinect for hand tracking and rendering in wearable haptics. IEEE World Haptics. Istanbul, Turkey: [s. n], pp.317-321, (2011).

DOI: 10.1109/whc.2011.5945505

[7] OpenKinect Organization. Imaging information for Kinect[EB/OL]. [2013-02-10]. http: /openkinect. org/wiki/Imaging_Information.

[8] W Andrew, S Mubarak, D Vitoria. A virtual 3D blackboard: 3D finger tracking using a single camera. IEEE International Conference on Automatic Face and Gesture Recognition, pp.536-543, (2000).

DOI: 10.1109/afgr.2000.840686

[9] Cem Keskin, Furkan Kirac. Randomized Decision Forests for Static and Dynamic Hand Shape Classification. Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on, pp.31-36, (2012).

DOI: 10.1109/cvprw.2012.6239183