Transliteration of Hiragana and Katakana Handwritten Characters Using CNN-SVM

https://doi.org/10.22146/ijccs.66062

Nicolaus Euclides Wahyu Nugroho(1*), Agus Harjoko(2)

(1) Master Program of Computer Science, FMIPA UGM, Yogyakarta
(2) Department of Computer Science and Electronics, FMIPA UGM, Yogyakarta
(*) Corresponding Author

Abstract


Hiragana and katakana handwritten characters are often used when writing words in Japanese. Japanese itself is often used by native Japanese as well as people learning Japanese around the world. Hiragana and katakana characters themselves are difficult to learn because many characters are similar to one another. In this study, hiragana and basic katakana, dakuten, handakuten, and youon were used, which were taken from the respondents using a questionnaire. This study used the CNN method which will be compared with a combination of the CNN and SVM methods which have been designed to identify each character that has been prepared. Preprocessing of character images uses the methods of image resizing, grayscaling, binarization, dilation, and erosion. The preprocessed results will be input for CNN as a feature extraction tool and SVM as a tool for character recognition. The results of this study obtained accuracy with the following parameters: 69×69 image size, 3 patience values, val_loss monitor callbacks, Nadam optimization function, 0.001 learning rate value, 30 epochs value, and SVM RBF kernel. If using a system that only uses the CNN network, the accuracy is 87.82%. The results obtained when using a combination of CNN and SVM were 88.21%.

Keywords


Character-Recognition; SVM; CNN; Deep-Learning; Japanese Character Recognition

Full Text:

PDF


References

[1]      V. Kumar, “Online Handwriting Recognition Problem : Issues and Techniques,” vol. 4, no. 1, pp. 16–24, 2014.

[2]      Charlie Tsai, “Recognizing Handwritten Japanese Characters Using Deep Convolutional Neural Networks,” pp. 1–7, 2016.

[3]      Y. Wang, P. Yu, and C. Li, “Offline Handwritten New Tai Lue Characters Recognition Using CNN-SVM,” Proc. 2019 IEEE 2nd Int. Conf. Electron. Inf. Commun. Technol. ICEICT 2019, pp. 636–639, 2019, doi: 10.1109/ICEICT.2019.8846292.

[4]      Darmatasia and M. I. Fanany, “Handwriting recognition on form document using convolutional neural network and support vector machines (CNN-SVM),” 2017 5th Int. Conf. Inf. Commun. Technol. ICoIC7 2017, vol. 0, no. c, pp. 1–6, 2017, doi: 10.1109/ICoICT.2017.8074699.

[5]      D. T. Mane and U. V Kulkarni, “Visualizing and Understanding Customized Convolutional Neural Network for Recognition of Handwritten Marathi Numerals,” Procedia Comput. Sci., vol. 132, no. Iccids, pp. 1123–1137, 2018, doi: 10.1016/j.procs.2018.05.027.

[6]      A. Dehghanian and V. Ghods, “Farsi Handwriting Digit Recognition based on Convolutional Neural Networks,” 2018 6th Int. Symp. Comput. Bus. Intell., vol. 1, pp. 65–68, 2018, doi: 10.1109/ISCBI.2018.00022.

[7]      M. Rajnoha, R. Burget, and M. Khisore Dutta, “Handwriting Comenia Script Recognition with Convolutional Neural Network,” pp. 775–779, 2017.

[8]      I.-J. Kim and X. Xie, “Handwritten Hangul recognition using deep convolutional neural networks,” pp. 1–13, 2015, doi: 10.1007/s10032-014-0229-4.

[9]      D. Suryani, P. Doetsch, and H. Ney, “On the Benefits of Convolutional Neural Network Combinations in Offline Handwriting Recognition,” 2016 15th Int. Conf. Front. Handwrit. Recognit., pp. 193–198, 2016, doi: 10.1109/ICFHR.2016.0046.

[10]    N. T. Ly, C. T. Nguyen, K. C. Nguyen, and M. Nakagawa, “Deep Convolutional Recurrent Network for Segmentation-Free Offline Handwritten Japanese Text Recognition,” Proc. Int. Conf. Doc. Anal. Recognition, ICDAR, vol. 7, pp. 5–9, 2018, doi: 10.1109/ICDAR.2017.357.

[11]    A. Shahariar, A. Rabby, S. Haque, S. Islam, S. Abujar, and S. A. Hossain, “BornoNet : Bangla Handwritten Characters Recognition Using Convolutional Neural Network Convolutional Neural Network,” Procedia Comput. Sci., vol. 143, pp. 528–535, 2018, doi: 10.1016/j.procs.2018.10.426.



DOI: https://doi.org/10.22146/ijccs.66062

Article Metrics

Abstract views : 342 | views : 500

Refbacks

  • There are currently no refbacks.




Copyright (c) 2021 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.



Copyright of :
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
ISSN 1978-1520 (print); ISSN 2460-7258 (online)
is a scientific journal the results of Computing
and Cybernetics Systems
A publication of IndoCEISS.
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Fax: +62274 555133
email:ijccs.mipa@ugm.ac.id | http://jurnal.ugm.ac.id/ijccs



View My Stats1
View My Stats2