Abstract
Deep learning based methods have been extensively used in Handwritten Chinese Character Recognition (HCCR) and significantly improved the recognition accuracy in recent years. Famous networks like GoogLeNet and deep residual network have been applied to this field and improved the recognition accuracy. While the structure of the neural network is crucial, the training methodology also plays an important role in deep learning based methods. In this paper, a new data generation method is proposed to increase the size of the training database. Chinese characters could be classified into different kinds of structures according to the radical components. Based on this, the proposed method segments the character images into sub-images and recombines them into new character samples. The generated database, including recombined characters and rotated characters, could improve the performance of current CNN models. We also apply the recently proposed and popular center loss function to further improve the recognition accuracy. Tested on ICDAR 2013 competition database, the proposed methods could achieve new state-of-the-art with a 97.53% recognition accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, X.Y., Bengio, Y., Liu, C.L.: Online and offline handwritten chinese character recognition: a comprehensive study and new benchmark. Pattern Recogn. 61, 348–360 (2017)
Cireşan, D., Meier, U.: Multi-column deep neural networks for offline handwritten Chinese character classification. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2015)
Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using googlenet and directional feature maps. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 846–850. IEEE (2015)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Liu, C.L., Yin, F., Wang, D.H., et al.: CASIA online and offline Chinese handwriting databases. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 37–41. IEEE (2011)
Chen, L., Wang, S., Fan, W., et al.: Beyond human recognition: a CNN-based framework for handwritten character recognition. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 695–699. IEEE (2015)
Yin, F., Wang, Q.F., Zhang, X.Y., et al.: ICDAR 2013 Chinese handwriting recognition competition. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1464–1470. IEEE (2013)
Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014)
Zhong, Z., Zhang, X.Y., Yin, F., et al.: Handwritten Chinese character recognition with spatial transformer and deep residual networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3440–3445. IEEE (2016)
Wu, C., Fan, W., He, Y., et al.: Handwritten character recognition by alternately trained relaxation convolutional neural network. In: 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 291–296. IEEE (2014)
Wen, Y., Zhang, K., Li, Z., et al.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., et al. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 11–26. Springer International Publishing, Heidelberg (2016). https://doi.org/10.1007/978-3-319-46478-7_31
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770–778. IEEE (2016)
Yang, S., Nian, F., Li, T.: A light and discriminative deep networks for off-line handwritten Chinese character recognition. In: Youth Academic Conference of Chinese Association of Automation, pp. 785–790 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Luo, W., Zhai, G. (2018). Offline Handwritten Chinese Character Recognition Based on New Training Methodology. In: Zhai, G., Zhou, J., Yang, X. (eds) Digital TV and Wireless Multimedia Communication. IFTC 2017. Communications in Computer and Information Science, vol 815. Springer, Singapore. https://doi.org/10.1007/978-981-10-8108-8_22
Download citation
DOI: https://doi.org/10.1007/978-981-10-8108-8_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8107-1
Online ISBN: 978-981-10-8108-8
eBook Packages: Computer ScienceComputer Science (R0)