Indonesian Batik Image Classification Using Statistical Texture Feature Extraction Gray Level Co-occurrence Matrix (GLCM) and Learning Vector Quantization (LVQ)

Authors

  • Nafik’ah Yunari Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia.
  • Eko Mulyanto Yuniarno Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia. Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia.
  • Mauridhi Hery Purnomo Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia. Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia.

Keywords:

Batik, GLCM, Image, Indonesian Batik, LVQ, Texture Feature,

Abstract

Batik, as a cultural heritage from Indonesia, has two kinds of true batik, batik tulis or handwritten batik and batik cap or stamped batik. However, it is still difficult to discern what is really batik and which are not. So many clothes are claimed as batik whereas they aren’t. These pseudo batiks have spread on the market and become deceitful. The objective of this research is to obtain the pattern value of batik to recognize the real batik using feature texture extraction with Gray Level Cooccurrence Matrix (GLCM) as a method for extracting textural features and Artificial Neural Network Learning Vector Quantization (LVQ) as a method to classify. The result of this study shows the average accuracy of data training without normalization of 90.43% and data with normalization of 98.40%. While on data testing the average value of accuracy on the dataset without normalization of 92.79% and after normalization the average value is 98.98%, so the increase in the average value of accuracy of 8%.

Downloads

Download data is not yet available.

Downloads

Published

2018-05-31

How to Cite

Yunari, N., Yuniarno, E. M., & Purnomo, M. H. (2018). Indonesian Batik Image Classification Using Statistical Texture Feature Extraction Gray Level Co-occurrence Matrix (GLCM) and Learning Vector Quantization (LVQ). Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(2-3), 67–71. Retrieved from https://jtec.utem.edu.my/jtec/article/view/4195