Convolutional Neural Networks for Handwritten Javanese Character Recognition

https://doi.org/10.22146/ijccs.31144

Chandra Kusuma Dewa(1*), Amanda Lailatul Fadhilah(2), A Afiahayati(3)

(1) Department of Informatics, Universitas Islam Indonesia, Yogyakarta
(2) Department of Informatics, Universitas Islam Indonesia, Yogyakarta
(3) Department of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta
(*) Corresponding Author

Abstract


Convolutional neural network (CNN) is state-of-the-art method in object recognition task. Specialized for spatial input data type, CNN has special convolutional and pooling layers which enable hierarchical feature learning from the input space. For offline handwritten character recognition problem such as classifying character in MNIST database, CNN shows better classification result than any other methods. By leveraging the advantages of CNN over character recognition task, in this paper we developed a software which utilizes digital image processing methods and CNN module for offline handwritten Javanese character recognition. The software performs image segmentation process using contour and Canny edge detection with OpenCV library over captured handwritten Javanese character image. CNN will classify the segmented image into 20 classes of Javanese letters. For evaluation purposes, we compared CNN to multilayer perceptron (MLP) on classification accuracy and training time. Experiment results show that CNN model testing accuracy outperforms MLP accuracy although CNN needs more training time than MLP.

Keywords


convolutional neural network; handwritten character recognition; Javanese character recognition

Full Text:

PDF


References

[1] E. Nurhayati, Mulyana, H. Mulyani, and Suwardi, “Strategi pemertahanan Bahasa Jawa di Provinsi Daerah Istimewa Yogyakarta,” LITERA: Jurnal Penelitian Bahasa, Sastra, dan Pengajarannya, vol. 12, no. 1, pp. 159-166, 2013. [Online]. Available: https://journal.uny. ac.id/index.php/litera/article/view/1338. [Accessed 12 August 2017].

[2] A. R. Widiarti and P. N. Wastu, “Javanese character recognition using hidden Markov model,” International Journal of Computer, Electrical, Automation, Control and Information Engineering, vol. 3, no. 9, pp. 2201-2204, 2009. [Online]. Available: http://waset.org/publications/10027/javanese-character-recognition-using-hidden-markov- model. [Accessed 2 January 2017].

[3] A. H. Nurul, M. D. Sulistiyo, and R. N. Dayawati, “Pengenalan Aksara Jawa tulisan tangan menggunakan directional element feature dan multi class support vector machine,” in Prosiding Konferensi Nasional Teknologi Informasi dan Aplikasinya, 13 September 2014, Palembang, Indonesia [Online]. Available: http://seminar.ilkom.unsri.ac.id/index.php/ kntia/article/view/733 /409. [Accessed: 4 February 2017]

[4] B. Isnawati, “Analisis implementasi jaringan syaraf tiruan backpropagation untuk klasifikasi huruf dasar Aksara Jawa,” Undergraduate Thesis, Department of Electrical Engineering and Information Technology, Universitas Gadjah Mada, Yogyakarta, 2015.

[5] M. C. Wibowo, I. D. G. R. Mardiana, and S. Wirakusuma, “Pengenalan pola tulisan tangan Aksara Jawa menggunakan multilayer perceptron,” in Prosiding Seminar Nasional Teknologi Informasi dan Multimedia, 6-8 February 2015, Yogyakarta, Indonesia [Online]. Available: http://ojs.amikom.ac.id/index.php/semnasteknomedia/article/view/907. [Acc- essed: 10 March 2017].

[6] N. B. Arum, “Pengenalan pola Aksara Jawa nglegena berbasis wavelet dan jaringan syaraf tiruan backpropagation,” Undergraduate Thesis, Department of Electrical Engineering and Information Technology, Universitas Gadjah Mada, Yogyakarta, 2016.

[7] G. S. Budhi and R. Adipranata, “Handwritten Javanese character recognition using several artificial neural network methods,” Journal of ICT Research and Applications, vol. 8, no. 3, pp. 195-212, 2015. [Online]. Available: http://journals.itb.ac.id/index.php/jictra/article/ view/769. [Accessed 5 July 2017].

[8] K. Syaban and A. Harjoko, “Klasifikasi varietas cabai berdasarkan morfologi daun menggunakan backpropagation neural network,” (IJCCS) Indonesian Journal of Computing and Cybernetics Systems, vol. 10, no. 2, pp. 161-172, 2016. [Online]. Available: https://journal.ugm.ac.id/ijccs/article/view/16628. [Accessed 15 April 2017].

[9] Herman and A. Harjoko, “Pengenalan spesies gulma berdasarkan bentuk dan tekstur daun menggunakan jaringan syaraf tiruan,” (IJCCS) Indonesian Journal of Computing and Cybernetics Systems, vol. 9, no. 2, pp. 207-218, 2015. [Online]. Available: https://journal. ugm.ac.id/ijccs/article/view/7549. [Accessed 11 February 2017].

[10] S. Aliaji and A. Harjoko, “Identifikasi barcode pada gambar yang ditangkap kamera digital menggunakan metode JST,” (IJCCS) Indonesian Journal of Computing and Cybernetics Systems, vol. 7, no. 2, pp. 121-132, 2013. [Online]. Available: https://journal.ugm.ac.id /ijccs/article/view/3351. [Accessed 9 May 2017].

[11] S. Zubair and A. Solichin, “Pengenalan karakter sandi rumput pramuka menggunakan jaringan syaraf tiruan dengan metode backpropagation,” in Prosiding Seminar Nasional Teknologi Informasi dan Multimedia, 4 February 2017, Yogyakarta, Indonesia [Online]. Available: http://ojs.amikom.ac.id/index.php/semnasteknomedia/article/view/1764. [Acc- essed: 10 August 2017].

[12] P. Sermanet, S. Chintala, and Y. LeCun, “Convolutional neural networks applied to house numbers digit classification,” in Proceedings of 2012 21st IEEE International Conference on Pattern Recognition (ICPR), 11-15 November 2012, Tsukuba, Japan [Online]. Available: http://ieeexplore.ieee.org/document/6460867/. [Accessed: 10 March 2017].

[13] Q. Li, W. Cai, X. Wang, Y. Zhou, D. D. Feng, and M. Chen, “Medical image classification with convolutional neural network,” in Proceedings of 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 10-12 December 2014, Singapore, Singapore [Online]. Available: http://ieeexplore.ieee.org/document/7064414/. [Accessed: 4 June 2017].

[14] G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for LVCSR using rectified linear units and dropout,” in Proceedings of 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 26-31 May 2013, Vancouver, Canada [Online]. Available: http://ieeexplore.ieee.org/document/6639346/. [Accessed: 7 June 2017].

[15] N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014. [Online]. Available: http://jmlr.org/papers/ volume15/srivastava14a/srivastava14a.pdf. [Accessed 5 May 2017].

[16] X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in Proceedings of International Conference on Artificial Intelligence and Statistics, 13-15 May 2010, Sardinia, Italy [Online]. Available: http://proceedings.mlr. press/v9/glorot10a/glorot10a.pdf. [Accessed: 11 July 2017].



DOI: https://doi.org/10.22146/ijccs.31144

Article Metrics

Abstract views : 11297 | views : 8627

Refbacks

  • There are currently no refbacks.




Copyright (c) 2018 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