Implementation of Real-time Handwriting Recognition System Using Touch Panel Based on Neural Network

Based on neural network, this study contributes to propose a real-time handwriting recognition system with Arabic numbers and lowercase letters. It includes two parts which are hardware design and software algorithm. In hardware design, after pressing the touch panel surface, analog signals are obtained and transformed into digital ones by A/D converter. In software algorithm, recognition architecture is constructed by three level backpropagation neural network and learning samples of Arabic numbers and lowercase letters are collected from nine schoolmates. Based on the illustration, the proposed handwriting recognition system of this study can achieve about 90% correction rates and satisfy the market standard. [Yi-Sung Yang, Cheng-Fang Huang, Bo-Jhih Hu, Teh-Lu Liao, Jun-Juh Yan. Implementation of Real-time Handwriting Recognition System Using Touch Panel Based on Neural Network. Life Sci J 2012;9(3):148-154] (ISSN:1097-8135). http://www.lifesciencesite.com. 20

[1]  Yanping Gao,et al.  Application of BP neural network in the digital recognition system , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[2]  John D. Hey,et al.  AN EXPERIMENTAL ANALYSIS , 2004 .

[3]  T. Saba,et al.  Off-line cursive script recognition: current advances, comparisons and remaining problems , 2012, Artificial Intelligence Review.

[4]  Amjad Rehman,et al.  Performance analysis of character segmentation approach for cursive script recognition on benchmark database , 2011, Digit. Signal Process..

[5]  Ghazali Sulong,et al.  Dynamic Programming Based Hybrid Strategy for Offline Cursive Script Recognition , 2010, 2010 Second International Conference on Computer Engineering and Applications.

[6]  Amjad Rehman,et al.  Neural networks for document image preprocessing: state of the art , 2014, Artificial Intelligence Review.

[7]  Heikki Handroos,et al.  Application of neural network in suppressing mechanical vibration of a permanent magnet linear motor , 2008 .

[8]  Amjad Rehman,et al.  An automatic approach for line detection and removal without smash-up characters , 2011 .

[9]  Zili Chen,et al.  A Handwriting Numeral Character Recognition System , 2010, 2010 International Conference on Multimedia Technology.

[10]  Amjad Rehman,et al.  DOCUMENT SKEW ESTIMATION AND CORRECTION: ANALYSIS OF TECHNIQUES, COMMON PROBLEMS AND POSSIBLE SOLUTIONS , 2011, Appl. Artif. Intell..

[11]  RehmanAmjad,et al.  Off-line cursive script recognition , 2012 .

[12]  Amit Choudhary,et al.  Performance analysis of feed forward MLP with various activation functions for handwritten numerals recognition , 2010, 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

[13]  Mazhar Mahmoud Hefnawi,et al.  Forecasting gamma radiation levels using digital image processing , 2012 .

[14]  Xinbo Zhang,et al.  Handwritten Digit Recognition Based on Improved Learning Rate BP Algorithm , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[15]  Amjad Rehman,et al.  Methods and strategies on off-line cursive touched characters segmentation: a directional review , 2014, Artificial Intelligence Review.