Kinect Depth Image Processing for Hand Motion Recognition using Backpropagation Neural Network

Syamsiar Kautsar, Purwadi A. Darwito, Sryang T. Sarena

Abstract


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.

Keywords


Kinect camera; depth image; neural network

Full Text:

PDF

References


Ren, Zhou, et all., “Robust Part-Based Hand Gesture Recognition Using Kinect Sensor”, IEEE Transactions on Multimedia, Vol. 15, No. 5, pg. 1110-1120, 2013.

Tashev, Ivan, “Kinect Development Kit: A Toolkit for Gesture-and Speech-Based Human-Machine Interaction”, IEEE Signal Processing Magazine, 2013, pg. 129-131.

Megalingam, R.K., et all., “Kinect Based Gesture Controlled Robotic Arm: A research work at HuT Labs”, IEEE International Conference in MOOC, Innovation and Technology in Education (MITE), pg. 294-299.

Kofman, Jonathan, Wu, Xianghai, Luu, T.J., and Verma, Siddharth, “Teleoperation of a Robot Manipulator using a Vision-Based Human-Robot Interface”, IEEE Transactions on Industrial Electronics, Vol. 52, No. 5, pg. 1206-1219,2005.

Kadir, Abdul, Dasar Pengolahan Citra dengan Delphi, Yogyakarta: Penerbit Andi, 2013.

Purnomo, Hery Mauridhi and Kurniawan, Agus, Supervised Neural Networks dan Aplikasinya, Yogyakarta: Graha Ilmu, 2006.




DOI: http://dx.doi.org/10.12962/j23546026.y2015i1.1044

Refbacks

  • There are currently no refbacks.


View my Stat: Click Here

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.