Study of Digital Character Recognition Based on BP Neural Networks

Abstract:

A digital character recognition method is presented based on BP Neural Network. This paper preprocesses the digital character image and extracts character feature, then uses BP Neural Network to recognize digital character. Back Propagation algorithm seeks network weights to minimize training error in the solution space. A network with hidden layer is created at first, then an input sample vector is sent to network input terminal and the square error E between output values and training sample object output values is calculated. Above process is repeated for input samples of training sets until the error is reduced within the limits of the threshold. The results show that the method presented has good accuracy, quick speed and strong robustness for realtime application.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 856-859
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.856
• Online since: July 2013
• Authors: Shuai Yuan, Guo Yun Zhang, Jian Hui Wu, Long Yuan Guo
• Keywords: Back Propagation Algorithm (BPA), BP Neural Network (BPNN), Digital Character Recognition, Training Sample

References

[1] Chenqin Gu,Wancheng Ge: Based on Template Matching Method. Journal of Communications Technology. Vol. 42 (2009), pp.220-222 (In Chinese)

[2] Cuichi Ren, Shuying Yang, Jun Hong: Handwritten character recognition based on BP neural network. Journal of Tianjin University of Technology. Vol. 22 (2006), pp.80-82 (In Chinese)

[3] Yishen Xu, Jihua Gu, Zhi Tao, Di Wu, Mingcheng Wu: Handwritten Character Recognition based on Improved BP Neural Network. Journal of Communications Technology. Vol. 44 (2011), pp.106-109 (In Chinese)

[4] Zheng Zhang, Yanping Wang, Guixiang Xue: Digital Image Processing and Machine Vision. (Posts & Telecom Press, Beijing 2010) (In Chinese)