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

Irma Amelia Dewi; Amelia Shaneva

doi:10.15575/join.v6i2.653

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

Irma Amelia Dewi, Amelia Shaneva

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%.

Keywords

CNN; Image Processing; Korean Language; Korean Syllables; VGG

Full Text:

PDF

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.