Jurnal INFOTEL
Vol 15 No 1 (2023): February 2023

The combination of color-texture features and machine learning for detecting Dayak beads

Anindita Septiarini (Universitas Mulawarman, Indonesia)
Hamdani Hamdani (Universitas Mulawarman, Indonesia)
Edy Winarno (Universitas Stikubank, Indonesia)



Article Info

Publish Date
01 Feb 2023

Abstract

Dayak is one of the tribes in East Kalimantan, Indonesia, which has a lot of cultural wealth. Beads craft is one of the Dayak traditional cultures made using various materials with distinctive motifs. The Dayak beads have many different motifs and color combinations. Hence not everyone can distinguish between the bead motif of Dayak and non-Dayak easily. This study aims to develop a bead detection method to differentiate between the bead types of Dayak and non-Dayak. The main processes required include preprocessing, feature extraction, and classification. The features were extracted based on color and texture. Experiments were carried out using several machine learning approaches. The highest results were achieved using the combination of color and texture features with the implementation of K-Nearest Neighbor (KNN) methods as indicated by the parameters precision, recall, and accuracy achieved of 92%, 92%, and 92.2% using Cross-Validation with a K-Fold value of 10.

Copyrights © 2023






Journal Info

Abbrev

infotel

Publisher

Subject

Computer Science & IT Electrical & Electronics Engineering

Description

Jurnal INFOTEL is a scientific journal published by Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) of Institut Teknologi Telkom Purwokerto, Indonesia. Jurnal INFOTEL covers the field of informatics, telecommunication, and electronics. First published in 2009 for a printed version and published ...