Application of VGG Architecture to Detect Korean Syllables Based on Image Text

Authors

  • Irma Amelia Dewi Department of Informatics, Institut Teknologi Nasional Bandung, Indonesia
  • Amelia Shaneva Department of Informatics, Institut Teknologi Nasional Bandung, Indonesia

DOI:

https://doi.org/10.15575/join.v6i2.653

Keywords:

CNN, Image Processing, Korean Language, Korean Syllables, VGG

Abstract

Korean culture began to spread widely throughout the world, ranging from lifestyle, music, food, and drinks, and there are still many exciting things from this Korean culture. One of the interesting things to learn is to know Korean letters (Hangul), which are non-Latin characters. If the Hangul letters have been learned, the next thing that lay people must learn is the Korean syllables, which are different from the Indonesian syllables. Because of the difficulty of learning Korean syllables, understanding a sentence needed a system to recognize Korean syllables. Therefore, in this study designing a system to acknowledge Korean syllables, the method used is Convolutional Neural Network with VGG architecture. The system performs the process of detecting Korean syllables based on models that have been trained using 72 syllable classes. The tests on 72 Korean syllable classes obtain an average accuracy of 96%, an average precision value of 96%, an average recall value of 100%, and an average F1 score of 98%.

References

RAHOTNI SITIO, "FENOMENA HALLYU PADA KOMUNITAS KOREAN CULTURAL CENTRE MEDAN (KCCM) DI KOTA MEDAN," Universitas Negeri Medan, 2017.

M. Yulius Harjoseputro S.T., "CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK PENGKLASIFIKASIAN AKSARA JAWA," Universitas Atma Jaya Yogyakarta, 2018.

Olga Russakovsky, J. Deng., Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei, "ImageNet Large Scale Visual Recognition Challenge," 2014.

Sang-Geol Lee, Yunsick Sung, Yeon-Gyu Kim and Eui-Young Cha, "Variations of AlexNet and GoogLeNet to Improve Korean Character Recognition Performance," Journal Of Information Processing Systems, 2018.

Wei Yu, Kuiyuan Yang, Yalong Bai, Tianjun Xiao, Hongxun Yao and Yong Rui, "Visualizing and Comparing AlexNet and VGG using Deconvolutional Layers," arXiv:1412.6631, 2014.

K. Andri, Analisa Sistem Informasi, Yogyakarta: Graha Ilmu, 2004.

G. T. Situmorang, A. W. Widodo and M. A. Rahman, "Penerapan Metode Gray Level Cooccurence Matrix (GLCM) untuk Ekstraksi Ciri pada Telapak Tangan," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 2019.

A. Hwa, C. Yong, R. Adinda, S. Agung and F. Hutagalung, "Bahasa Korea Terpadu untuk Orang Indonesia," Yu Hyun-seok: Seoul, 2013.

Karen Simonyan and Andrew Zisserman, "VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION," University of Oxford, 2014.

I. Suartika E. P, A. Wijaya and Soelaiman, "Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) Pada Caltech 101," Jurnal Teknik ITS, 2016.

D. Pedamonti, Comparison of non-linear activation functions for deep neural networks on MNIST Classification Task, Machine Learning, 2018.

D. Nielsen, "Deep Learning Cage Match: Max Pooling vs Convolutions," 9 September 2018. [Online]. Available: https://medium.com/@duanenielsen/deep-learning-cage-match-max-pooling-vs-convolutions-e42581387cb9.

Christopher Albert Lorentius, Rudy Adipranata and Alvin Tjondrowiguno, "Pengenalan Aksara Jawa dengan Menggunakan Metode Convolutional Neural Network," Universitas Kristen Petra, 2019.

A. T. Wicaksono, "Prediksi Kepribadian Berdasarkan Tulisan Tangan Dengan Metode Convolutional Neural Network," Universitas Komputer Indonesia, 2019.

C. D. Manning, P. Raghavan and H. Schütze, An Introduction to Information Retrieval, Cambridge: Cambride University Press, 2009.

Downloads

Published

2021-12-26

Issue

Vol. 6 No. 2 (2021)

Section

Article

Citation Check

License

You are free to:

 

Under the following terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.

  • NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.

  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

 

Notices:

  • You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.
  • No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

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

Similar Articles

1 2 3 4 5 6 7 > >> 

You may also start an advanced similarity search for this article.