Abstract
Nowadays, there is a great demand for multilingual optical character recognition (MOCR) in various web applications. And recently, Long Short-Term Memory (LSTM) networks have yielded excellent results on Latin-based printed recognition. However, it is not flexible enough to cope with challenges posed by web applications where we need to quickly get an OCR model for a certain set of languages. This paper proposes a Hybrid Model Reuse (HMR) training approach for multilingual OCR task, based on 1D bidirectional LSTM networks coupled with a model reuse scheme. Specifically, Fixed Model Reuse (FMR) scheme is analyzed and incorporated into our approach, which implicitly grabs the useful discriminative information from a fixed text generating model. Moreover, LSTM layers from pre-trained networks for unilingual OCR task are reused to initialize the weights of target networks. Experimental results show that our proposed HMR approach, without assistance of any post-processing techniques, is able to effectively accelerate the training process and finally yield higher accuracy than traditional approaches.
Supported by the National Social Science Foundation of China (Grant No: 15BGL048), the Hubei Province Science and Technology Support Project (Grant No: 2015BAA072), the National Natural Science Foundation of China (Grant No. 61672398), the Hubei Provincial Natural Science Foundation of China (Grant No: 2017CFA012), the Fundamental Research Funds for the Central Universities (WUT: 2017II39GX).
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
Similar content being viewed by others
References
Ablavatski, A., Lu, S., Cai, J.: Enriched deep recurrent visual attention model for multiple object recognition. In: Applications of Computer Vision, pp. 971–978 (2017)
Baird, H.S.: Document image defect models and their uses. In: 2nd International Conference Document Analysis and Recognition, ICDAR 1993, Tsukuba City, Japan, 20–22 October 1993, pp. 62–67 (1993)
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (2002)
Breuel, T.M.: The OCRopus open source OCR system. In: Proceedings of the Document Recognition and Retrieval XV, Part of the IS&T-SPIE Electronic Imaging Symposium, San Jose, CA, USA, 29–31 January 2008, p. 68150F (2008)
Firmani, D., Merialdo, P., Nieddu, E., Scardapane, S.: In codice ratio: OCR of handwritten Latin documents using deep convolutional networks. In: International Workshop on Artificial Intelligence for Cultural Heritage, pp. 9–16 (2017)
Graves, A., Gomez, F.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: International Conference on Machine Learning, pp. 369–376 (2006)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105 (2012)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: International Conference on International Conference on Machine Learning, pp. 97–105 (2015)
Naz, S., Umar, A.I., Shirazi, S.H., Ajmal, M.M., Salahuddin: The optical character recognition for cursive script using HMM: a review. Res. J. Appl. Sci. Eng. Technol. 8(19), 2016–2025 (2014)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Peng, X., Cao, H., Setlur, S., Govindaraju, V., Natarajan, P.: Multilingual OCR research and applications: an overview. In: International Workshop on Multilingual OCR, pp. 1–8 (2013)
Philip, B., Samuel, R.D.S.: A novel bilingual OCR system based on column-stochastic features and SVM classifier for the specially enabled. In: Second International Conference on Emerging Trends in Engineering & Technology, pp. 252–257 (2009)
Shi, Z., Shi, M., Li, C.: The prediction of character based on recurrent neural network language model. In: IEEE/ACIS International Conference on Computer and Information Science, pp. 613–616 (2017)
Smith, R., Antonova, D., Lee, D.S.: Adapting the tesseract open source OCR engine for multilingual OCR. In: International Workshop on Multilingual OCR, p. 1 (2009)
Song, R., Umemoto, K., Nie, J., Xie, X., Tanaka, K., Rui, Y.: UniClip: leveraging web search for universal clipping of articles on mobile. Data Sci. Eng. 1(2), 101–113 (2016)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Ul-Hasan, A., Breuel, T.M.: Can we build language-independent OCR using LSTM networks? In: International Workshop on Multilingual OCR, p. 9 (2013)
Yang, B., Zhang, Y., Cao, J., Zou, L.: On road vehicle detection using an improved faster RCNN framework with small-size region up-scaling strategy. In: Satoh, S. (ed.) PSIVT 2017. LNCS, vol. 10799, pp. 241–253. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-92753-4_20
Yang, Y., Zhan, D., Fan, Y., Jiang, Y., Zhou, Z.: Deep learning for fixed model reuse. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, California, USA, 4–9 February 2017, pp. 2831–2837 (2017)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, Quebec, Canada, 8–13 December 2014, pp. 3320–3328 (2014)
Zhou, Z.H.: Learnware: On the Future of Machine Learning. Springer, New York (2016)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Xie, Z., Li, L., Zhong, X., Zhong, L., Xie, Q., Xiang, J. (2018). A Hybrid Model Reuse Training Approach for Multilingual OCR. In: Hacid, H., Cellary, W., Wang, H., Paik, HY., Zhou, R. (eds) Web Information Systems Engineering – WISE 2018. WISE 2018. Lecture Notes in Computer Science(), vol 11233. Springer, Cham. https://doi.org/10.1007/978-3-030-02922-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-02922-7_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02921-0
Online ISBN: 978-3-030-02922-7
eBook Packages: Computer ScienceComputer Science (R0)