Principle Component Analysis Based Hand Gesture Recognition for Android Phone Using Area Features

Hand gesture has been used in different applications and implemented on different platforms. Hence, a real-time and robust approach with high recognition accuracy is important in smart devices. This paper describes a novel method of hand gesture recognition using Principle Component Analysis (PCA) implemented in Android phone. Area features are adopted to do the gesture recognition. It solves these problems such as different size of gesture image captured, different angle of gesture¡¯s rotation and flipped gesture. Experiment results show that the average recognition rate of the proposed method is 93.95%.  Moreover, the computation complexity of the proposed method is low, and it can be adopted in real-time applications.

[1]  Houssem Lahiani,et al.  Real time hand gesture recognition system for android devices , 2015, 2015 15th International Conference on Intelligent Systems Design and Applications (ISDA).

[2]  Ankit Chaudhary,et al.  Real-time hand gesture recognition in FPGA , 2016 .

[3]  Yang Luo,et al.  A Method of Gesture Segmentation Based on Skin Color and Background Difference Method , 2013 .

[4]  B. D. Avinash,et al.  Color hand gesture segmentation for images with complex background , 2013, 2013 International Conference on Circuits, Power and Computing Technologies (ICCPCT).

[5]  Yael Edan,et al.  Vision-based hand-gesture applications , 2011, Commun. ACM.

[6]  Tae-Seong Kim,et al.  3-D hand motion tracking and gesture recognition using a data glove , 2009, 2009 IEEE International Symposium on Industrial Electronics.

[7]  Graham Horton,et al.  A new approach for touch gesture recognition: Conversive Hidden non-Markovian Models , 2015, J. Comput. Sci..

[8]  M. Iqbal Saripan,et al.  Skin Segmentation Using YUV and RGB Color Spaces , 2014, J. Inf. Process. Syst..

[9]  Wenjun Tan,et al.  Gesture segmentation based on YCb'Cr' color space ellipse fitting skin color modeling , 2012, 2012 24th Chinese Control and Decision Conference (CCDC).

[10]  Nikos Papamarkos,et al.  Hand gesture recognition using a neural network shape fitting technique , 2009, Eng. Appl. Artif. Intell..

[11]  Sukhdip Singh,et al.  HAND GESTURE RECOGNITION TECHNIQUES : A REVIEW , 2015 .

[12]  Heung-Il Suk,et al.  Hand gesture recognition based on dynamic Bayesian network framework , 2010, Pattern Recognit..

[13]  Daijin Kim,et al.  Simultaneous Gesture Segmentation and Recognition based on Forward Spotting Accumulative HMMs , 2006, 18th International Conference on Pattern Recognition (ICPR'06).