CNN for Image Identification of Hiragana Based on Pattern Recognition using CNN

Chaerul Umam, Andi Danang Krismawan, Rabei Raad Ali

Abstract


Hiragana is one of the letters in Japanese. In this study, CNN (Convolutional Neural Network) method used as identication method, while he preprocessing used thresholding. Then carry out the normalization stage and the filtering stage to remove noise in the image. At the training stage use maxpooling and danse methods as a liaison in the training process, wherea in testing stage using the Adam Optimizer method. Here, we use 1000 images from 50 hiragana characters with a ratio of 950: 50, 950 as training data and 50 data as testing data. Our experiment yield accuracy in 95%.


Full Text:

PDF

References


C. L. Liu, “Normalization-cooperated gradient feature extraction for handwritten character recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 8, pp. 1465–1469, 2007.

Y. Wang, Z. Lian, Y. Tang, and J. Xiao, “Boosting scene character recognition by learning canonical forms of glyphs,” Int. J. Doc. Anal. Recognit., vol. 22, no. 3, pp. 209–219, 2019.

Q. Miao, R. Liu, P. Zhao, Y. Li, and E. Sun, “A Semi-supervised Image Classification Model based on Improved Ensemble Projection Algorithm,” IEEE Access, vol. 4, no. c, pp. 1–1, 2017.

S. D. Budiwati, J. Haryatno, and E. M. Dharma, “Japanese character (Kana) pattern recognition application using neural network,” in Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011, 2011, no. July.

M. Karki, Q. Liu, R. DiBiano, S. Basu, and S. Mukhopadhyay, “Pixel-level reconstruction and classification for noisy handwritten bangla characters,” Proc. Int. Conf. Front. Handwrit. Recognition, ICFHR, vol. 2018-August, pp. 511–516, 2018.

F. Chang, C. C. Lin, and C. J. Chen, “Applying a hybrid method to handwritten character recognition,” in Proceedings - International Conference on Pattern Recognition, 2004, vol. 2, no. 1, pp. 529–532.

M. Nguyen and N. A. V. B, “SVMs with Deep Learning and Random,” in Springer, vol. 2, Springer International Publishing, 2019, pp. 157–172.

S. Das and S. Banerjee, “An Algorithm for Japanese Character Recognition,” Int. J. Image, Graph. Signal Process., vol. 7, no. 1, pp. 9–15, 2014.

H. A. Morsy, “Developing a New CCN Technique for Arabic Handwritten Digits Recognition,” Int. J. Recent Technol. Eng., vol. 9, no. 3, pp. 520–524, 2020.

Charlie Tsai, “Recognizing Handwritten Japanese Characters Using Deep Convolutional Neural Networks,” 2016.

H. Shah, R. Rajasekaran, and J. Masih, “A Comparative Study of Classification Algorithms with Varying Training Dataset Sizes on Cursive Hiragana Characters,” J. Xi’an Univ. Archit. Technol., vol. XII, no. Viii, pp. 1388–1396.




DOI: https://doi.org/10.33633/jais.v6i2.4586

Article Metrics

Abstract view : 384 times
PDF - 236 times

Refbacks

  • There are currently no refbacks.


Flag Counter

 

 

 

 

Journal of Applied Intelligent System (e-ISSN : 2502-9401, p-ISSN : 2503-0493) is published by Department of Informatics Universitas Dian Nuswantoro Semarang and IndoCEISS.

  

 

Journal of Applied Intelligent System indexed by :


This journal is under licensed of Creative Commons Attribution 4.0 International License.

Visitor Stats