Abstract
This paper presents a segment and recognize approach to recognize Vietnamese online handwritten text, which is inspired from divide and conquer algorithm. First, we propose two segmentation methods to divide a handwritten paragraph into multiple text lines (text line segmentation) and then multiple words (word segmentation). Secondly, an end to end deep neural network model is developed to recognize Vietnamese handwritten words. Our model is derived from the success of the recent deep neural network models for offline handwriting recognition on English, Chinese, and Japanese. Due to the fact that Vietnamese online handwritten patterns commonly consist of many delayed strokes which are caused by diacritic marks, our approach is to render the online patterns to offline images and recognize them by a deep neural network. Although the offline images rendered from the online patterns are not completely same as the real offline images, they are still good enough to recognize. Besides, the proposed line and word segmentation methods have achieved the segmentation accuracy of 96.67% for line segmentation and 89.47% for word segmentation. Using the segmented handwritten words, the connectionist temporal classification loss with combining of convolutional layers and long short term memory layer are employed. The best recognition accuracy is 95.31% for characters and 88.80% for words, which show the promising results and could be improved in future by further research on different neural network structures.
REFERENCES
Biadsy, F., Saabni, R., and El-Sana, J., Segmentation free online Arabic handwriting recognition, Int. J. Pattern Recognit. Artif. Intell., 2011, vol. 25, no. 7, pp. 1009–1033. https://doi.org/10.1142/S021800141100895
Zhu, B. and Nakagaw, M., Online handwritten Chinese/Japanese character recognition, Advances in Character Recognition, Ding, X., Ed., InTech, 2012, pp. 51–68. https://doi.org/10.5772/51474
Doetsch, P., Kozielski, M., and Ney, H., Fast and robust training of recurrent neural networks for offline handwriting recognition, 2014 14th Int. Conf. on Frontiers in Handwriting Recognition, Hersonissos, Greece, 2014, IEEE, 2014, pp. 279–284. https://doi.org/10.1109/icfhr.2014.54
Le, B.H., Le, T.H., and Hoang, K., A fuzzy neural network for Vietnamese character recognition, Proc. 1999 Int. Conf. on Image Processing, Kobe, Japan, 1999, IEEE, 1999, pp. 585–589. https://doi.org/10.1109/ICIP.1999.821697
Quan, V.H., Trung, P.N., and Ha, N.D.H., A robust method for the Vietnamese handwritten and speech recognition, 2002 Int. Conf. on Pattern Recognition, Quebec City, Canada, 2002, vol. 3, pp. 732–735. https://doi.org/10.1109/ICPR.2002.1048080
Nguyen, D.Kh. and Bui, T.D., Recognizing Vietnamese online handwritten separated characters, 2008 Int. Conf. on Advanced Language Processing and Web Information Technology, Dalian, China, 2008, IEEE, 2008, pp. 279–284. https://doi.org/10.1109/alpit.2008.58
Nguyen, H.T., Nguyen, C.T., Bao, P.T., and Nakagawa, M., A database of unconstrained Vietnamese online handwriting and recognition experiments by recurrent neural networks, Pattern Recognit., 2018, vol. 78, pp. 291–306. https://doi.org/10.1016/j.patcog.2018.01.013
Nguyen, H.T., Nguyen, C.T., and Nakagawa, M., ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018), 2018 16th Int. Conf. on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, N.Y., 2018, IEEE, 2018, pp. 494–499. https://doi.org/10.1109/icfhr-2018.2018.00092
Sun, Z., Jin, L., Xie, Z., Feng, Z., and Zhang, Sh., Convolutional multi-directional recurrent network for offline handwritten text recognition, 2016 15th Int. Conf. on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China, 2016, IEEE, 2016. https://doi.org/10.1109/icfhr.2016.0054
Pham, V., Bluche, T., Kermorvant, C., and Louradour, J., Dropout improves recurrent neural networks for handwriting recognition, 2014 14th Int. Conf. on Frontiers in Handwriting Recognition, Hersonissos, Greece, 2014, IEEE, 2014, pp. 285–290. https://doi.org/10.1109/icfhr.2014.55
Simonyan, K. and Zisserman, A., Very deep convolutional networks for large-scale image recognition, Proc. Int. Conf. Learning Representations, 2015.
Le, A.D., Nguyen, H.T., and Nakagawa, M., An end-to-end recognition system for unconstrained Vietnamese handwriting, SN Comput. Sci., 2020, vol. 1, no. 1, p. 7. https://doi.org/10.1007/s42979-019-0001-4
Funding
This research was supported by the scientific research fund of Vietnam National University Ho Chi Minh City (VNUHCM) and University of Information Technology (UIT-VNUHCM).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Viet Hang Duong, Nguyen, H.T., Nakagawa, M. et al. A Novel Approach for Vietnamese Handwritten Text Recognition. Aut. Control Comp. Sci. 57, 534–541 (2023). https://doi.org/10.3103/S014641162305005X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S014641162305005X