Javanese Character Feature Extraction Based on Shape Energy

Galih Hendra Wibowo, Riyanto Sigit, Aliridho Barakbah

Abstract


Javanese character is one of Indonesia's noble culture, especially in Java. However, the number of Javanese people who are able to read the letter has decreased so that there need to be conservation efforts in the form of a system that is able to recognize the characters. One solution to these problem lies in Optical Character Recognition (OCR) studies, where one of its heaviest points lies in feature extraction which is to distinguish each character. Shape Energy is one of feature extraction method with the basic idea of how the character can be distinguished simply through its skeleton. Based on the basic idea, then the development of feature extraction is done based on its components to produce an angular histogram with various variations of multiples angle. Furthermore, the performance test of this method and its basic method is performed in Javanese character dataset, which has been obtained from various images, is 240 data with 19 labels by using K-Nearest Neighbors as its classification method. Performance values were obtained based on the accuracy which is generated through the Cross-Validation process of 80.83% in the angular histogram with an angle of 20 degrees, 23% better than Shape Energy. In addition, other test results show that this method is able to recognize rotated character with the lowest performance value of 86% at 180-degree rotation and the highest performance value of 96.97% at 90-degree rotation. It can be concluded that this method is able to improve the performance of Shape Energy in the form of recognition of Javanese characters as well as robust to the rotation.


Full Text:

PDF

References


R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification (2Nd Edition). Wiley-Interscience, 2000.

V. K. GOVINDAN and A. P. SHIVAPRASA, “CHARACTER RECOGNITION - A REVIEW,” Pattern Recognit., vol. 23, pp. 671–683, 1990.

A. M. S, “HANACARAKA : Javanese script that began to be abandoned,” Surakarta, 2011.

M. Hossain, M. Amin, and H. Yan, “Rapid Feature Extraction for Optical Character Recognition,” arXiv Prepr. arXiv1206.0238, pp. 1–5, 2012.

O. D. Trier, A. K. Jain, and T. Taxt, “Feature extraction methods for character recognition - A survey,” Pattern Recognit., vol. 29, no. 4, pp. 641–662, 1996.

S. Mozaffari, “A Hybrid Structural/Statistical Classifier for Handwritten Farsi/Arabic Numeral Recognition.,” 2005.

B. Ariani, M. Pertiwi, A. R. Barakbah, and Y. Setiowati, “Jurnal Informatika dan Pengenalan Pola Penulisan Kata Aksara Jawa Pada Piranti Bergerak Dengan Shape Independent Clustering,” 2013.

G. S. Budhi and R. Adipranata, “Java characters recognition using evolutionary neural network and combination of Chi2 and backpropagation neural network,” Int. J. Appl. Eng. Res., 2014.

G. S. Budhi and R. Adipranata, “Handwritten Javanese Character Recognition Using Several Artificial Neural Network Methods,” J. ICT Res. Appl., vol. 8, no. 3, pp. 195–212, 2015.

S.-T. Bow, Pattern Recognition and Image Preprocessing. Second Edition, Revised and Expanded. 2002.

M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine Vision, vol. 1542. 1993.

N. Otsu, “A Threshold Selection Method from Gray-Level Histogram,” 1979.

Y. S. Chen and W. H. Hsu, “A modified fast parallel algorithm for thinning digital patterns,” Pattern Recognit. Lett., vol. 7, no. 2, pp. 99–106, 1988.

G. H. Wibowo, R. Sigit, and A. Barakbah, “Feature Extraction of Character Image using Shape Energy,” pp. 471–475, 2016.

D. Hand, D. Hand, H. Mannila, H. Mannila, P. Smyth, and P. Smyth, Principles of data mining, vol. 30. 2001.




DOI: 10.24003/emitter.v5i1.175

Refbacks

  • There are currently no refbacks.


Copyright (c) 2017 EMITTER International Journal of Engineering Technology

EMITTER Journal Editorial Office

 

Politeknik Elektronika Negeri Surabaya

Jl. Raya ITS - Kampus PENS Sukolilo Surabaya 60111, INDONESIA

emitter@pens.ac.id   http://emitter.pens.ac.id   Telp : +62 31 594 7280   Fax : +62 31 594 6114