Abstract
This paper proposes the offline Myanmar handwriting recognition system which uses the combination of deep learning approaches- convolutional neural networks to extract features from the input images and recurrent neural networks to recognize these features. To improve the performance of the system, some pre-processing techniques such as binarization, noise removing, image segmentation and resizing, are also applied before training the scanned images. The experiment is carried out on the own dataset related with office staff leave form documents since there is no free resources for Myanmar language. Performance of the proposed system is evaluated using both the character error rate (CER) and the word error rate (WER).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zaidan, A.A., Zaidan, B.B., Jalab, H.A., Alanazi, H.O., Alnaquib, R.: Offline Arabic handwriting recognition using artificial neural network. J. Comput. Sci. Eng. 1(1), 55–58 (2010)
Sawy, A.E., Loey, M., Bakry, H.E.: Arabic handwritten characters recognition using convolutional neural network. WSEAS Trans. Comput. Res. 5 (2017). E-ISSN: 2415–1521
Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural network. In: NIPS: Neural Information Processing Systems Conference (2008)
Balci, B., Saadati, D., Shiferaw, D.: Handwritten Text Recognition using Deep Learning, CS231n: Convolutional Neural Networks for Visual Recognition. Stanford University, Course Project Report (2017)
Alwzwazy, H.A., Albehadili, H.M., Alwan, Y.S., Islam, N.E.: Handwritten digit recognition using convolutional neural network. Int. J. Innov. Res. Comput. Commun. Eng. 4(2), 1101–1106 (2016)
Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.V.: Improving convolutional neural network, recurrent neural network hybrid networks for handwriting recognition. In: ICFHR: 16th International Conference on Frontiers in Handwriting Recognition (2018)
Hamid, N.B A., Sjarif, N.N.B.A.: Handwritten recognition using support vector machine, k nearest neighbor and neural network. arXiv: 1702.00723v1 [cs.CV], Feburary 2017
Kumbhar, O., Kunjir, A.: A survey on optical handwriting recognition system using machine learning algorithms. Int. J. Comput. Appl. 175, 8887 (2017)
Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural network. In: ICPR: Proceedings of the 21st International Conference on Pattern Recognition, November 2012
Acknowledgements
The authors would like to give special thanks to the advisers from University of Information Technology who have given valuable ideas during the development of the proposed system and professors who have given advice and suggestion from the language point of view. Moreover, we would also like to thank the Rector and the administration department for allowing to use the data of office documents for the proposed system.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Win, H.Y., Wai, T.T. (2020). Implementation of Myanmar Handwritten Recognition. In: Vasant, P., Zelinka, I., Weber, GW. (eds) Intelligent Computing and Optimization. ICO 2019. Advances in Intelligent Systems and Computing, vol 1072. Springer, Cham. https://doi.org/10.1007/978-3-030-33585-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-33585-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33584-7
Online ISBN: 978-3-030-33585-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)