Abstract
Handwritten Uyghur character recognition researches up to date have been based on traditional pattern recognition techniques that highly relies on handcrafted features. The similarity between character forms has been hindering the extraction of robust features. This paper proposed the deep learning based self-learned features to recognize 128 handwritten Uyghur characters forms. The first-hand online handwritten trajectory is first preprocessed and converted to a centralized binary image as input to the implemented deep neural network model. In experiments, the convolutional neural network models with 4, 5 and 8 convolutional layers are studied to get higher recognition accuracy. All models are trained implementing the same dropout regularization. The models 8 convolutional layers on 48 * 48 converted character images produced as high as 94.65% average accuracy on a test set of 10,240 handwritten character samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gao, Y., Jin, L., He, C., Zhou, G.: Handwriting character recognition as a service: a new handwriting recognition system based on cloud computing. In: 2011 International Conference on Document Analysis and Recognition, Beijing, pp. 885–889 (2011)
Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: Online and offline handwritten Chinese character recognition: benchmarking on new databases. Pattern Recognit. 46(1), 155–162 (2013)
Okamoto, M., Yamamoto, K.: Online handwriting character recognition method using directional and direction-change features. Int. J. Pattern Recognit. Artif. Intell. 13(7), 1041–1059 (1999)
Alom, M.Z., Sidike, P., Hasan, M., et al.: Handwritten Bangla character recognition using the state-of-art deep convolutional neural networks. Comput. Intell. Neurosci. 2018, 1–3 (2017)
Kurban, A., Mamat, H.: Beida FangZheng Uighur text to unicode text code codeconversion. J. Xinjiang Univ. (Nat. Sci. Ed.) 23(3), 343–347 (2006)
Simayi, W., Ibrayim, M., Tursun, D., et al.: Survey on the features for recognition of on-line handwritten Uyghur characters. Int. J. Signal Process. Image Process. Pattern Recognit. 8(3), 850–853 (2015)
Dawut, R.: Research on the key technologies of online handwritten Uyghur word recognition, M.S. thesis, Xinjiang University (2011)
Simayi, W.: Online Uyghur handwritten character recognition technology based on center distance feature, MS thesis, Xinjiang University (2014)
Ibrayim, M.: Key technologies for recognition of on-line handwritten Uyghur characters and words. Ph.D. thesis, Wuhan University (2013)
Dai, X.L.: Online handwritten Uyghur character and word recognition based on the mobile platform. MS thesis, Xidian University (2012)
Xu, Y.M.: A study of key techniques for Uighur handwriting recognition. Ph.D. dissertation, Xidian University (2014)
Liu, C.L.: Normalization-cooperated gradient feature extraction for handwritten character recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1465 (2007)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)
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. Curran Associates Inc. (2012)
Acknowledgment
This work is supported by National Key Research and Development Plan of China (2017YFC0820603), Natural Science Youth Foundation of Universities in Autonomous Region (No. XJEDU2019Y007) and Natural Science Foundation of Xinjiang (No. 2020D01C045). The first author is very much grateful to the National Laboratory of Pattern Recognition of CASIA for providing the experimental environment.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Simayi, W., Ibrayim, M., Hamdulla, A. (2021). Handwritten Uyghur Character Recognition Using Convolutional Neural Networks. In: Song, H., Jiang, D. (eds) Simulation Tools and Techniques. SIMUtools 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 370. Springer, Cham. https://doi.org/10.1007/978-3-030-72795-6_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-72795-6_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72794-9
Online ISBN: 978-3-030-72795-6
eBook Packages: Computer ScienceComputer Science (R0)