TRANSLITERASI CITRA AKSARA HIRAGANA MEMPERGUNAKAN JARINGAN BACKPROPAGATION

  • Nicolaus Euclides Wahyu Nugroho Teknik Informatika Universitas Sanata Dharma Paingan Maguwoharjo Depok Sleman Yogyakarta
  • Anastasia Rita Widiarti Teknik Informatika Universitas Sanata Dharma Paingan Maguwoharjo Depok Sleman Yogyakarta
Keywords: Backpropagation, Hiragana Character Recognition, Intensity of Character, Mark Direction

Abstract

The purpose of this research is to understand the ability and to find out how much percentage of accuracy of Back Propagation algorithm in Japanese characters handwriting Hiragana’s pattern recognition. This study used the characterization of calculating a black pixel (intensity of character) and calculating the direction by applying masking diagonal left, right diagonal, vertical, and horizontal (mark direction). There were 797 letters that can be read correctly by backpropagation test equipment after applying feature combination 6 on the 7th test. Combination 6 had 5 charaterization feature 1, feature 2, feature 3, feature 4, and feature 5. Each feature was a colective feature of 9 segment which had explanation like this : feature 1 was Intensity of Character (Black), feature 2 was Mark Direction Diagonal 1 (Diag1), feature 3 was Mark Direction Diagonal 2 (Diag2), feature 4 was Mark Direction Horisontal (Horz) , and feature 5 was Mark Direction Vertical (Vert). This study revealed succeeded in proving that the
backpropagation algorithm was able to recognize Hiragana letters after achieving a success rate of accuracy above 85% which was 86.63%.S

Downloads

Download data is not yet available.

References

[1] Putra, D. (2010). Pengolahan Citra Digital Menggunakan Matlab.Yogyakarta : Andi Offset.

2] Lalujan, T.F. (tanpa tahun). Mudah Menulis Dan Membaca Huruf Hiragana Dan Huruf Katakana Dalam Bahasa Jepang.
http://www.academia.edu/6228224/MENULIS_DAN_MEMBACA_HURUF_HIRAGANA _DAN_HURUF_KATAKANA_PEMULA. 7 Juni 2016.

[3] Kurniawan, H.P. (2008). Pengenalan Huruf Jepang Katakana Menggunakan Logika Kabur. Skripsi. Fakultas Sains dan Teknologi. Universitas Sanata Dharma. Yogyakarta.

[4] Fathia, S. (tanpa tahun). Penerapan Jaringan Syaraf Tiruan Dalam Pengenalan Tulisan Tangan Huruf Korea (Hangul) Menggunakan Metode Propagasi Balik. http://eprints.dinus.ac.id/11905/1/jurnal_11611.pdf. 25 Mei 2016. Fakultas Studi Teknik Informatika, Universitas Dian Nuswantoro. Semarang.

[5] Nurmila, N. Sugiharto, A. & Sarwoko, E.A. (tanpa tahun). Algoritma Back Propagation Neural Network Untuk Pengenalan Pola Karakter Huruf Jawa.http://ejournal.undip.ac.id/index.php/jmasif/article/download/74/521. 5 Juni 2016.

[6] Basuki, A. (2005). Image Enhancement. http://basuki.lecturer.pens.ac.id/lecture/sesi4citra.pdf. 15 Juli 2016.

[7] Matlab. (tanpa tahun). Multilayer Neural Network Architecture.
http://www.mathworks.com/help/nnet/ug/multilayer-neural-networkarchitecture. html. 5 Juli 2016.

[8] Siang, J.J. (2009). Jaringan Syaraf Tiruan dan Pemrogramannya Menggunakan Maltab. Yogyakarta : Andi Offset.

[9] Surinta, O. (2010). Overview of Handwritten Thai character Recognition. http://www.ai.rug.nl/~mrolarik/APSMeeting/09-07-
2010%20Overview%20of%20Handwritten%20Thai%20Character%20Recognition.pdf. 12 Mei 2016.

[10] Widiarti, A.R. (2011). Comparing Hilditch, Rosenfeld, Zhang-Suen, Nagendraprasad – Wang-Gupta Thinning.International Scholarly and Scientific Research & Innovation. No 6. Vol 5. halaman 1. http://waset.org/publications/6492/comparing-hilditch-rosenfeld-zhang-suenand-nagendraprasad-wang-gupta-thinning.
Published
2016-08-31
Section
Articles