Abstract
Increased accuracy in predictive models for handwritten character recognition will open up new frontiers for optical character recognition. Major drawbacks of predictive machine learning models are headed by the elongated training time taken by some models, and the requirement that training and test data be in the same feature space and consist of the same distribution. In this study, these obstacles are minimized by presenting a model for transferring knowledge from one task to another. This model is presented for the recognition of handwritten numerals in Indic languages. The model utilizes convolutional neural networks with backpropagation for error reduction and dropout for data overfitting. The output performance of the proposed neural network is shown to have closely matched other state-of-the-art methods using only a fraction of time used by the state-of-the-arts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Thrun, S.: Is learning the n-th thing any easier than learning the first? In: Advances in Neural Information Processing Systems, pp. 640–646 (1996)
Caruana, R.: Multitask learning. In: Learning to Learn, pp. 95–133. Springer, Berlin (1998)
Raina, R., Battle, A., Lee, H., Packer, B., Ng, A.Y.: Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th International Conference on Machine Learning, pp. 759–766 (2007)
Hayashi, T.: Bakhshali Manuscript. Encycl. Hist. Sci. Technol. Med. Non-Western Cult. 387–389 (2008)
Crump, T.: The Anthropology of Numbers. Cambridge University Press, Cambridge (1992)
Ifrah, G., Harding, E.F., Bellos, D., Wood, S., et al.: The Universal History of Computing: From the Abacus to Quantum Computing. Wiley, USA (2000)
Smith, D.E., Karpinski, L.C.: The Hindu-Arabic Numerals. Courier Corporation, USA (2013)
Struik, D.J.: A Concise History of Mathematics. Courier Corporation, USA (2012)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 439–440 (2015)
Wu, X., Kumar, V., Quinlan, J.R., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G.J., Ng, A., Liu, B., Philip, S.Y.: others: top 10 algorithms in data mining. Knowl. Inf. Syst. 14, 1–37 (2008)
Pradhan, A.: Support vector machine-A survey. Int. J. Emerg. Technol. Adv. Eng. 2, 82–85 (2012)
Hoffmann, A.G., et al.: General limitations on machine learning. In: ECAI, pp. 345–347 (1990)
Yang, Q., Chen, Y., Xue, G.-R., Dai, W., Yu, Y.: Heterogeneous transfer learning for image clustering via the social web. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, vol. 1, pp. 1–9 (2009)
Ling, X., Xue, G.-R., Dai, W., Jiang, Y., Yang, Q., Yu, Y.: Can chinese web pages be classified with english data source? In: Proceedings of the 17th International Conference on World Wide Web, pp. 969–978 (2008)
Cireşan, D.C., Meier, U., Schmidhuber, J.: Transfer learning for Latin and Chinese characters with deep neural networks. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–6 (2012)
Al-Mubaid, H., Umair, S.A.: A new text categorization technique using distributional clustering and learning logic. IEEE Trans. Knowl. Data Eng. 18, 1156–1165 (2006)
Maitra, D. Sen, Bhattacharya, U., Parui, S.K.: CNN based common approach to handwritten character recognition of multiple scripts. In: 13th International Conference on Document Analysis and Recognition (ICDAR), 2015, pp. 1021–1025 (2015)
Hinton, G.E., Salakhutdinov, R.R.: Replicated softmax: an undirected topic model. In: Advances in Neural Information Processing Systems, pp. 1607–1614 (2009)
Clevert, D.-A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (elus). arXiv Prepr. arXiv1511.07289. (2015)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Google Code Archieve—Long-term Storage for Google Code Project Hosting. https://code.google.com/archive/p/cmaterdb/downloads
Ashiquzzaman, A., Tushar, A.K.: Handwritten Arabic numeral recognition using deep learning neural networks. In: IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR), 2017, pp. 1–4 (2017)
Acknowledgements
The authors would like to thank the department of Computer Science and Engineering, University of Asia Pacific for supporting this research in various ways. Abdul Kawsar Tushar and Akm Ashiquzzaman contributed equally to this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Tushar, A.K., Ashiquzzaman, A., Afrin, A., Islam, M.R. (2018). A Novel Transfer Learning Approach upon Hindi, Arabic, and Bangla Numerals Using Convolutional Neural Networks. In: Hemanth, D., Smys, S. (eds) Computational Vision and Bio Inspired Computing . Lecture Notes in Computational Vision and Biomechanics, vol 28. Springer, Cham. https://doi.org/10.1007/978-3-319-71767-8_83
Download citation
DOI: https://doi.org/10.1007/978-3-319-71767-8_83
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-71766-1
Online ISBN: 978-3-319-71767-8
eBook Packages: EngineeringEngineering (R0)