The Community for Technology Leaders
2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD) (2016)
Shanghai, China
May 30, 2016 to June 1, 2016
ISBN: 978-1-5090-0804-9
pp: 287-291
Mengmeng Han , State Key Laboratory on Integrated Optoelectronics, Jilin University, Chang Chun, China
Jiajun Chen , State Key Laboratory on Integrated Optoelectronics, Jilin University, Chang Chun, China
Ling Li , State Key Laboratory on Integrated Optoelectronics, Jilin University, Chang Chun, China
Yuchun Chang , State Key Laboratory on Integrated Optoelectronics, Jilin University, Chang Chun, China
ABSTRACT
Hand gestures are a type of communication that is multifaceted in a number of ways and they provide an attractive alternative to the cumbersome interface devices used for human-computer interaction (HCI). However, there are still limitations regarding its usage in unfavorable live situations where hand gestures variation, illumination change or background complexity are an issue. Therefore, this paper propose a convolution neural network (CNN) method to reduce the difficulty of gestures recognition from a camera image. To achieve the robustness performance, the skin model and background subtraction are applied to obtain the training and testing data for the CNN. Since the light condition seriously affects the skin color, we adopt a simple Gaussian skin color model to robustly filter out non-skin colors of an image. In addition, it also employs elastic distortions to obtain lager database for more effective training and reduce potential overfitting. Experimental evaluation achieves an average correct classification rate of 93.8%, which shows the feasibility andreliability of the method.
INDEX TERMS
Image color analysis, Convolution, Skin, Neural networks, Gesture recognition, Training, Robustness
CITATION

M. Han, J. Chen, L. Li and Y. Chang, "Visual hand gesture recognition with convolution neural network," 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), Shanghai, China, 2016, pp. 287-291.
doi:10.1109/SNPD.2016.7515915
98 ms
(Ver 3.3 (11022016))