Batik Classification using Texture Analysis and Multiclass Support Vector Machine

Wahyu Tri Puspitasari, Dian Candra Rini Novitasari, Wika Dianita Utami

2018

Abstract

Batik is one of the cultural heritage has become an Indonesian identity and recognized by the Organization of Education, Science and Cultural Organization (UNESCO). Every region in Indonesia has very diverse batik motifs. There are 38 batik motifs based on the area of origin. It will be difficult to recognize each of these patterns while batik began to be liked by many local and foreign tourists. Therefore, a system is needed that can recognize every pattern of batik to facilitate people in recognizing batik motifs. Support Vector Machine (SVM) has excellent performance in classification and can also be used to recognize patterns of batik motif. We use the Gray Level Co-occurrence Matrix (GLCM) for feature extraction and SVM for batik classification. The result show that batik motif can be classified using SVM with 96% accuracy for two types of batik motifs, 88.89% for three types of batik motifs and 77.14% for four types of batik motifs.

Paper Citation

in Harvard Style

Puspitasari W., Novitasari D. and Utami W. (2018). Batik Classification using Texture Analysis and Multiclass Support Vector Machine.In Proceedings of the International Conference on Mathematics and Islam - Volume 1: ICMIs, ISBN 978-989-758-407-7, pages 65-71. DOI: 10.5220/0008517300650071

in Bibtex Style

@conference{icmis18,
author={Wahyu Tri Puspitasari and Dian Candra Rini Novitasari and Wika Dianita Utami},
title={Batik Classification using Texture Analysis and Multiclass Support Vector Machine},
booktitle={Proceedings of the International Conference on Mathematics and Islam - Volume 1: ICMIs,},
year={2018},
pages={65-71},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008517300650071},
isbn={978-989-758-407-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Mathematics and Islam - Volume 1: ICMIs,
TI - Batik Classification using Texture Analysis and Multiclass Support Vector Machine
SN - 978-989-758-407-7
AU - Puspitasari W.
AU - Novitasari D.
AU - Utami W.
PY - 2018
SP - 65
EP - 71
DO - 10.5220/0008517300650071