Kinect Depth Image Processing for Hand Motion Recognition Using Backpropagation Neural Network
暂无分享,去创建一个
Kinect RGB-D Camera is a sensor for human gesture recognition. Kinect has built-in infrared array sensor which produces a depth image data. In this research, the depth image data is used to recognize human hand condition. The depth images of human right hand are processed by normalized central moment method. Furthermore, the moment value of hand depth image is used for backpropagation artificial neural network data training. A great training result is yielded by 70% accuracy. In addition, the output of neural netwok model is used to control a robot hand.
[1] Jonathan Kofman,et al. Teleoperation of a robot manipulator using a vision-based human-robot interface , 2005, IEEE Transactions on Industrial Electronics.
[2] Abdul Kadir. Dasar Pengolahan Citra dengan Delphi , 2013 .
[3] Ivan Tashev. Kinect Development Kit: A Toolkit for Gesture- and Speech-Based Human-Machine Interaction [Best of the Web] , 2013, IEEE Signal Processing Magazine.