Abstract
There is a significant style overfitting problem in traditional content supervision models of character recognition: insufficient generalization ability to recognize the characters with unseen font styles. To overcome this problem, in this paper we propose a novel framework named Style and Content Supervision (SCS) network, which integrates style and content supervision to resist style overfitting. Different from traditional models only supervised by content labels, SCS simultaneously leverages the style and content supervision to separate the task-specific features of style and content, and then mixes the style-specific and content-specific features using bilinear model to capture the hidden correlation between them. Experimental results prove that the proposed model is able to achieve the state-of-the-art performance on several widely used real world character sets, and it obtains relatively strong robustness when the size of training set is shrinking.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, L., Wang, S., Fan, W., Sun, J.: Beyond human recognition: a CNN-based framework for handwritten character recognition. In: IAPR Asian Conference on Pattern Recognition, pp. 695–699 (2015)
Dan, C., Meier, U.: Multi-column deep neural networks for offline handwritten Chinese character classification. In: International Joint Conference on Neural Networks, pp. 1–6 (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. Computer Science, pp. 580–587 (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Annual Conference on Neural Information Processing Systems 2012, NIPS 2012, Lake Tahoe, Nevada, United States, 3–6 December 2012, pp. 1106–1114 (2012)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates, Inc. (2012)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lv, G.: Recognition of multi-fontstyle characters based on convolutional neural network. In: Fourth International Symposium on Computational Intelligence and Design, pp. 223–225 (2011)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, pp. 91–99 (2015)
Schmidhuber, J., Meier, U., Ciresan, D.: Multi-column deep neural networks for image classification. In: Computer Vision and Pattern Recognition, pp. 3642–3649 (2012)
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, p. 958 (2003)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7–12 June 2015, pp. 1–9 (2015)
Tang, W., et al.: CNN-based Chinese character recognition with skeleton feature. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018, Part V. LNCS, vol. 11305, pp. 461–472. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04221-9_41
Tenenbaum, J.B., Freeman, W.T.: Separating style and content. In: Annual Conference on Neural Information Processing Systems 1996, NIPS 1996, Denver, CO, USA, 2–5 December 1996, pp. 662–668 (1996)
Wu, C., Fan, W., He, Y., Sun, J., Naoi, S.: Handwritten character recognition by alternately trained relaxation convolutional neural network. In: International Conference on Frontiers in Handwriting Recognition, pp. 291–296 (2014)
Xiao, X.F., Jin, L., Yang, Y., Yang, W., Sun, J., Chang, T.: Building fast and compact convolutional neural networks for offline handwritten chinese character recognition. Pattern Recogn. 72, 72–81 (2017)
Xu, N., Ding, X.: Printed Chinese character recognition via the cooperative block neural networks. In: IEEE International Symposium on Industrial Electronics, vol. 1, pp. 231–235 (1992)
Yin, F., Wang, Q.F., Zhang, X.Y., Liu, C.L.: ICDAR 2013 Chinese handwriting recognition competition (ICDAR), pp. 1464–1469 (2013)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhong, Z., Jin, L., Feng, Z.: Multi-font printed Chinese character recognition using multi-pooling convolutional neural network. In: International Conference on Document Analysis and Recognition, pp. 96–100 (2015)
Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using googlenet and directional feature maps. In: International Conference on Document Analysis and Recognition, pp. 846–850 (2015)
Acknowledgment
We thank all reviewers for their helpful advice. This work is supported by the National Key Research and Development Program of China, and National Natural Science Foundation of China (No. U163620068).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Tang, W., Jiang, Y., Gao, N., Xiang, J., Su, Y., Li, X. (2019). SCS: Style and Content Supervision Network for Character Recognition with Unseen Font Style. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1143. Springer, Cham. https://doi.org/10.1007/978-3-030-36802-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-36802-9_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36801-2
Online ISBN: 978-3-030-36802-9
eBook Packages: Computer ScienceComputer Science (R0)