cover
Contact Name
Dedy Yusman
Contact Email
dedy.yusman@stmikplk.ac.id
Phone
-
Journal Mail Official
jurnalsaintekom@stmikplk.ac.id
Editorial Address
Jl. George Obos No. 114, Kel. Menteng, Kec. Jekan Raya, Palangka Raya, 73112
Location
Kota palangkaraya,
Kalimantan tengah
INDONESIA
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen
Published by STMIK Palangka Raya
ISSN : 20881770     EISSN : 25033247     DOI : 10.33020
Core Subject : Science,
Jurnal Saintekom adalah singkatan dari Sains, Teknologi, Komputer dan Manajemen, merupakan jurnal ilmiah yang berfungsi sebagai media mengkomunikasikan ide, gagasan dan pemikiran seputar kajian aktual tentang sains, teknologi, komputer dan manajemen antarkademisi dan peneliti.
Articles 171 Documents
Penerapan Local Binary Pattern dan Multi-Class SVM untuk Klasifikasi Motif Tenun Timor Risald Risald; Budiman Baso; Debora Chrisinta
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Vol 16 No 2 (2026): September 2026
Publisher : STMIK Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33020/saintekom.v16i2.1099

Abstract

This study develops an automatic classification system for Timor weaving motifs using the Local Binary Pattern (LBP) method for feature extraction and Support Vector Machine (SVM) for classification. The study aims to facilitate and accelerate the identification of traditional Timor weaving motifs through the application of machine learning. The dataset consists of 1,500 images obtained through direct image acquisition and documentation of six Timor weaving motifs: Nunkolo, Futus Pelangi, Kemak, Kaimafafa, Mabuna, and Biboki. The research process includes image preprocessing, feature extraction using LBP with 8 sampling points and a radius of 1 pixel, and classification using multi-class SVM with the One-vs-One (OVO) strategy. For the six classes, the OVO strategy produces 15 binary classifiers evaluated using three kernels: Linear, Polynomial, and Radial Basis Function (RBF). The SVM parameters used are C = 1 and degree = 3. The evaluation results show that the Linear kernel provides the best performance, with an accuracy of 90.66%, precision of 90.96%, recall of 90.66%, and F1-score of 90.81%. The Polynomial and RBF kernels produce lower performance. These results indicate that the combination of LBP and OVO-SVM with the Linear kernel is effective for classifying six Timor weaving motifs and can serve as an image-based tool to assist in motif identification