Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika dan Teknologi Informasi
Moch. Ryan Nurfebrianto
Universitas Muhammadiyah Lamongan
Computer Science & IT

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

Found 1 Documents
Search

 1 
Implementasi Convolutional Neural Network (CNN) untuk Klasifikasi Citra Batik Nusantara Zufar Faiil Haq; Mufti Ari Bianto; Afifah Agustin; Moch. Ryan Nurfebrianto
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 1 (2025): April: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i1.5421

Abstract

Batik is a cultural heritage of the nation, with each batik having a unique and diverse pattern motif. The batik culture is very strong in Indonesia, so batik can be found in all regions of the archipelago. Each batik has its own characteristics and traits to distinguish itself in each area. However, many people find it difficult to differentiate the types of batik motif patterns, one of which is the Nusantara Megamendung batik. Therefore, this research aims to introduce the classification process of Nusantara batik motif patterns using one of the Deep Learning methods, namely Convolutional Neural Network (CNN), to differentiate the types of batik motif patterns in each region. The dataset is taken from the numeric representations of Red, Green, and Blue (RGB) values of each pixel, which are used as model learning features to study color patterns and textures. From the results of the experiments conducted, the batik image classification using the CNN method has a high level of accuracy The batik classification model achieved an accuracy of 85%, demonstrating a fairly good ability to identify batik images, one of which is the Mega Mendung batik. The Mega Mendung and Keraton classes showed perfect performance, with precision, recall, and F1-score close to 1.00. However, the Bali class was the main weak point, with a recall of only 60%, indicating that 40% of Bali Batik samples were misclassified, primarily as Keraton.
Co-Authors Afifah Agustin Mufti Ari Bianto Zufar Faiil Haq