Open Journal Systems

Research on Handwritten Chinese Character Recognition Based on BP Neural Network

Zihao Ning(China University of Geosciences Automation College)


The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before. Handwritten Chinese character recognition, as a hot research object in image pattern recognition, has many applications in people’s daily life, and more and more scholars are beginning to study off-line handwritten Chinese character recognition. This paper mainly studies the recognition of handwritten Chinese characters by BP (Back Propagation) neural network. Establish a handwritten Chinese character recognition model based on BP neural network, and then verify the accuracy and feasibility of the neural network through GUI (Graphical User Interface) model established by Matlab. This paper mainly includes the following aspects: Firstly, the preprocessing process of handwritten Chinese character recognition in this paper is analyzed. Among them, image preprocessing mainly includes six processes: graying, binarization, smoothing and denoising, character segmentation, histogram equalization and normalization. Secondly, through the comparative selection of feature extraction methods for handwritten Chinese characters, and through the comparative analysis of the results of three different feature extraction methods, the most suitable feature extraction method for this paper is found. Finally, it is the application of BP neural network in handwritten Chinese character recognition. The establishment, training process and parameter selection of BP neural network are described in detail. The simulation software platform chosen in this paper is Matlab, and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition. Design the GUI interface of human-computer interaction based on Matlab, show the process and results of handwritten Chinese character recognition, and analyze the experimental results.


Pattern recognition; Handwritten Chinese character recognition; BP neural network

Full Text:



Zhao, Zh.Ch., Luo, Z., Wang, P.Y., et al., 2020. Summary of research on network image classification algorithm based on depth residual. Application of Computer System. 29(1), 18-25.

Li, X.L., 2018. Printed Chinese character recognition based on BP neural network. Think Tank Era. 161(45), 193+195.

Wan, L.P., Lan, X.G., Zhang, H.B., et al., 2019. Summary of deep reinforcement learning theory and its application. Pattern recognition and artificial intelligence. 32(1), 67-81.

Liu, F., 2014. Research on character recognition algorithm based on improved BP neural network. Value Engineering. 33(10), 206-207.

Li, D., 2016. Multi-sample handwritten character recognition software based on BP neural network. 37(7), 103-108.

Yamamoto, S., Nakajima, A., Nakata, K., 1973. Chinese character recognition by hierarchical pattern matching. Pattern Recognition, International Conference. 187-196.

Sun, Q., 2007. Offline Handwritten Chinese Character Recognition System. Nanjing: Nanjing University of Aeronautics and Astronautics.

Zhang, Y., Li, E.L., 1999. Research on preprocessing algorithm in off-line handwritten Chinese character recognition. Journal of Shenyang University of Technology. 21(6), 534-535.

Wang, Q., Zhao, R.Ch., 2001. Standardization and Evaluation of Handwritten Chinese Characters. Data Collection and Processing. 16(2), 227-232.

Gao, Y.Y., 2004. Summary of unconstrained handwritten Chinese character segmentation methods. Computer Engineering. 30(5), 144-145.

Ding, S., Su, C., Yu, J., 2011. An optimizing BP neural network algorithm based on genetic algorithm. Artificial Intelligence Review. 36(2), 153-162.

Song, M.L., 2002. Median filtering algorithm for removing image noise. Journal of Luoyang Normal University. (5), 67-69.

Lin, K.K., Song, G.X., 2004. Comparison and improvement of image denoising methods. Journal of Xidian University (Natural Science Edition). 31(4), 627-628.

Zhang, X., Bengio, Y., Liu, C., 2017. Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark. Pattern Recognition. 61, 348-360.

Xue, B.R., Yang, J.Y., Lou, Zh., et al., 1999. Eliminating burrs and burrs of handwritten Chinese characters. Journal of Nanjing University of Science and Technology. 23(2), 49-52.

Zhuang, Y., Liu, Q., Qiu, C., et al., 2021. A handwritten Chinese character recognition based on convolutional neural network and median filtering. Journal of Physics: Conference Series. 1820(1), 012162.

Lian, W., Xu, B.Zh., 2007. A new feature extraction method in handwritten Chinese character recognition-elastic grid directional decomposition feature. Journal of Circuit and System. 2(3), 8-13.

Ma, Sh.P., Xia, Y., Zhu, X.Y., 2006. Research on handwritten Chinese character recognition based on directional line element method. Journal of Tsinghua University. 24-27.

Wan, L.Y., Chen, J.X., Wang, W.P., et al., 2006. Research on image recognition based on BP neural network. Journal of Wuhan University of Science and Technology. 29(3), 277-279.

Ning, B., Chen, J., Tan, J., 2019. The handwritten Chinese character recognition uses convolutional neural networks with the google net. International Journal of Pattern Recognition and Artificial Intelligence.

Xu, Y.Sh., Gu, J.H., Tao, Zh., et al., 2011. Handwritten character recognition based on improved BP neural network. Communication Technology. (5), 106-109.

Huang, Sh.Q., Zhao, Zh.Y., Sun, L.B., 2017. Improvement of BP neural network algorithm. Science and Technology Innovation Herald. 14(20), 146-147.

Ren, H.Y., Yuan, B.Sh., Pastoral, 2010. Uyghur Online Handwritten Character Recognition Based on BP Neural Network. Microelectronics and Computer. 27(8), 238-241.

Yu, H., Cao, L., Li, Q.Y., 2009.. Improvement of BP neural network algorithm and its application in handwritten Chinese character recognition. Journal of Jiangxi Normal University (Natural Science Edition). 33(05), 598-603.

Murru, N., Rossini, R., 2016. A Bayesian approach for initialization of weights in backpropagation neural net with application to character recognition. Neurocomputing. 193, 92-105.

Srivastava, N., Hinton, G., Krizhevsky, A., et al., 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research. 15(1), 1929-1958.

Redmon, J., Divvala, S., Girshick, R., et al., 2016. You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779-788.

Chen, K., 1977. Iterated path integral. Bulletin of The American Mathematical Society. 83(5), 831-879.

Liu, B., 2015. Application of improved image matching method in Chinese character recognition. Guangzhou: Jinan University.

Lian, W., Qin, J.Zh., 2004. Research on Gabor feature extraction method of elastic grid for handwritten Chinese character recognition. Computer Application Research. (12), 163-165.

Wang, F., 2021. Identification method of station state information based on image processing and neural network. Railway Communication Signal. 57(3), 60-63.

Chen, J.H., Yang, L.L., Zhao, Y.J., et al., 2021. Application of deep neural network model in logging electrical imaging image processing. Electronic Measurement Technology. 44(4), 138-143.



  • There are currently no refbacks.
Copyright © 2022 peng peng Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
  • :+65-98550280 QQ:2249355960