KLASIFIKASI MOTIF KAIN TRADISIONAL BATIK BOMBA KAILI BERDASARKAN FITUR TEKSTUR CITRA DIGITAL
Keywords:
classification, texture, batik Bomba, GLCM, LSVMAbstract
Batik Bomba is a traditional textile of Kaili ethnic located in Kota Palu of Sulawesi Tengah. Batik
Bomba is one of Indonesia's cultural richness which has unique patterns and motifs. The unique
patterns found in Batik Bomba have a philosophical meaning in the life of Kaili ethnic. Bomba
batik motif image has many varieties making it difficult to recognize every motive variety. To
recognize each motive image Batik Bomba we must be known special characteristics of each
motive. This research will classify traditional batik Bomba Kaili motif with the stage of acquisition,
preprocessing, texture feature extraction and classification stages. The texture features of Bomba
batik image are obtained from feature extraction process using Gray Level Co-occurrence matrices
(GLCM) with angles 0, 45, 90 and 135. The texture features of each Bomba batik motif will be
classified using Linear Support Vector Machine (LSVM) method. The results obtained in this study
is the value of classification accuracy based on the value of texture characteristics at an angle 0
of 74.2%, angle 45 of 64.5%, angle 90 of 66.7% and 135 of 67.5%. The merger of all features of
Batik Bomba motif image in all angles resulted in the accuracy of classification at the training
phase to 80.65% and in the testing phase yielded an accuracy of 77.14%.
References
Segmentation Using Hidden Markov
Tree Methods in Recognizing Motif of
Batik. Journal Of Theoretical and
Applied Information Technology, 85(1),
pp.27–33.
Boswell, D., 2002. Introduction to Support
Vector Machines,
Burges, C.J.C., 1997. A Tutorial on Support
Vector Machines for Pattern
Recognition,
Dong ping Tian, 2013. A Review on Image
Feature Extraction and Representation
Techniques. International Journal of
Multimedia and Ubiquitous
Engineering, 8(4), pp.385–396.
Haralick, R., Shanmugan, K. & Dinstein, I.,
1973. Textural features for image
classification. IEEE Transactions on Systems, Man and Cybernetics, 3,
pp.610–621. Available at:
http://dceanalysis.bigr.nl/Haralick73Textural
features for image
classification.pdf.
Kasim, A.A. & Harjoko, A., 2014.
Klasifikasi Citra Batik Menggunakan
Jaringan Syaraf Tiruan Berdasarkan
Gray Level Co- Occurrence Matrices (
GLCM ). In Seminar Nasional Aplikasi
Teknologi Informasi (SNATI).
Yogyakarta, pp. 7–13.
Kasim, A.A., Wardoyo, R. & Harjoko, A.,
2017. Batik Classification with
Artificial Neural Network Based on
Texture-Shape Feature of Main
Ornament. I.J. Intelligent Systems and
Applications, 9(June), pp.55–65.
Available at: http://www.mecspress.org/ijisa/v9n6.html.
Kasim, A.A., Wardoyo, R. & Harjoko, A.,
2016. Feature Extraction Methods for
Batik Pattern Recognition : A Review.
In AIP Conference Proceedings.
American Institute of Physics, pp. 1–8.
Langeron, Y.Ã. et al., 2007. Classifying NIR
spectra of textile products with kernel
methods. Engineering Application Of
Artificial Intelligence, 20, pp.415–427.
Mulaab, 2010. Ekstraksi Fitur Motif Batik
Berbasis Metode Statistik Tingkat
Tinggi. In Seminar Nasional
Informatika. pp. 69–75.
Nugroho, A.S., Witarto, A.B. & Handoko,
D., 2003. Support Vector Machine
“Teori dan Aplikasinya dalam
Bioinformatika.” In Proceeding of
Indonesian Scientific Meeting in
Central Japan, December 20, 2003.
Gifu-Japan.
Walid, M., Makruf, M. & Anwari, 2015.
Segmentasi Motif Batik Menggunakan
Metode K-Means Clustering. In
Seminar Nasional Humaniora Dan
Aplikasi Teknologi Informasi
(SEHATI). pp. 2–5.
