Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Sistem Informasi dan Manajemen
AKBAR, MUHAMAD DENI
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
KLASIFIKASI MOTIF BATIK JAWA MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBORS (KNN) AKBAR, MUHAMAD DENI; Martanto, Martanto; Wijaya, Yudhistira Arie
JURSIMA Vol 10 No 2 (2022): Jursima Vol. 10 No. 2, Agustus Tahun 2022
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47024/js.v10i2.412

Abstract

Batik is one of Indonesia's beautiful and well-known heritages throughout the world, batik as a traditional heritage of the archipelago comes with a variety of motifs. Each region has different motifs and different philosophies. The number of Indonesian batik motifs spread from Aceh to Papua, so not everyone can distinguish batik motifs. This study aims to distinguish between Javanese batik motifs and non-Javanese batik motifs. The batik motifs taken by researchers as samples from the Java region were the Mega Mendung batik motif, Lasem batik motif, Sekar Jagad batik motif, Kawung batik motifs and motifs, and for non-Javanese researchers took samples of Cendrawasih batik motifs, Dayak batik motifs, and batik motifs. nutmeg, and Balinese batik motifs. The research method uses the K-Nearest Neighbors (KNN) algorithm which has stages of collecting image on batik motifs, knowing Javanese and non-Javanese batik motifs, pre-processing, feature extraction, image classification, and evaluation of motifs. Color feature extraction is carried out using gray level co-occurrence matrix (GLCM) methods. Based on the test results show that with the application of GLCM and KNN with an image size ratio of 200x200 with a ratio of k=5 the percentage of split image 80% test and 20% training is able to produce an accuracy of 65%.
Co-Authors Martanto . Yudhistira Arie Wijaya