Writing in the Air Using Kinect and Growing Neural Gas Network
DOI:
https://doi.org/10.11113/jt.v72.3949Keywords:
Kinect, growing neural gas, multi-layer perceptron networkAbstract
This paper discusses an approach which helps us to recognize English language characters which are written in the air by hands. This method is done by using Kinect camera and growing neural gas network. The proposed character recognition method has three main steps: preprocessing, training and recognition. The system and the proposed method can be considered from two aspects: (a) runtime, and (b) accuracy. One of the main goals in this method is to provide noise tolerance which is necessary for these kinds of methods. IN addition, it has influence upon accuracy rate because the proposed method can remove more outliers. The results show that the proposed method provides good results with the accuracy rate of 95.54%, 97.86% and 99.08% for lower case letters, upper case letters and digits respectively.
References
V. Patil, S. Shimpi. 2011. Handwritten English Character Recognition Using Neural Network. Elixir Comp. Sci. & Engg. 41: 5587–5591.
M. Fahmy, H. El-Messiry. 1999. Zernike Moments As Feature Extracto for Arabic Character. The 1st-MINIA International Conference for Advanced Trends in Engineering, March 14–17.
D. Shi, S. R. Gunn, R. I Damper. 2003. Handwritten Chinese Radical Recognition Using Nonlinear Active Shape Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 25(2): 277–280.
R. Plamondon and C. M Privitera. 1999. The Segmentation of Cursive.
Handwriting: An Approach Based on Off-Line Recovery of the Motor-Temporal Information. IEEE Trans. Image Processing. 8(1): 80–91.
R. Plamondon , and Sargur N. Srihari. 2000. On-Line and Off-Line.
Handwriting Recognition: A Comprehensive Survey. IEEE Transactions
on Pattern Analysis and Machine Intelligence. 22(1): 63–84.
L. Xiaolin, and D.-Y Yeung,. 1997. On-line Handwritten Alphanumeric Character Recognition Using Dominant Points In Strokes. Pattern Recognition. 30(1): 31–44.
Kinect for Windows SDK 2.0 Public Preview: http://www.microsoft.com/en-us/download/details.aspx?id=43661.
G. Tesauro, D. S. Touretzky and T. K. Leen 1995. Advances in Neural Information Processing Systems 7. MIT Press, Cambridge MA.
G. Zhenning 2013. An Abstract of Parallel and Distributed Implementation of A Multilayer Perceptron Neural Network on A Wireless Sensor Network, Submitted to the Graduate Faculty as partial fulfillment of the requirements for the Master of Science Degree in Engineering, The University of Toledo.
O. Fink, E. Zio, & U. Weidmann, 2013. Predicting Time Series of Railway Speed Restrictions With Time-Dependent Machine Learning Techniques. Expert Systems with Applications. 40(15): 6033–6040.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
