Feature Extraction using Histogram of Oriented Gradients and Moments with Random Forest Classification for Batik Pattern Detection

Azizah, Wafiq (2025) Feature Extraction using Histogram of Oriented Gradients and Moments with Random Forest Classification for Batik Pattern Detection. Jurnal SISFOKOM (Sistem Informasi dan Komputer), 14 (1). pp. 8-14. ISSN 2581-0588

	Text Halaman persetujuan.pdf Download (310kB)
	Text Artikel.pdf Download (635kB)

Abstract

Thepreservationoftraditionalbatikpatterns,often transmittedorallyandthroughdirectpracticeacrossgenerations, faces significant challenges in the modern era. Globalization introduces the risk of cultural homogenization, potentially diminishing the uniqueness and diversity of these patterns. Furthermore, the manual recognition of batik motifs is labor-intensive, time-consuming, and requires specialized expertise, rendering it unsuitable for large-scale preservation initiatives. Consequently, the development of technology-based solutions capableofdocumenting,analyzing,andrecognizingbatikpatterns with efficiency and precision is imperative for safeguarding this cultural heritage. This study aims to address these challenges by developing an automated system for recognizing batik patterns, focusingonJavanesebatikmotifs—Kawung,Megamendung,and Parang—which serve as foundational designs for the evolution of batik in other regions. The proposed methodology integrates two feature extraction techniques, Histogram of Oriented Gradients (HOG) and Texture Moments, with the Random Forest machine learning algorithm. The research process encompasses four key stages: pre-processing, feature extraction, classification, and systemevaluation,wheretheaccuracyofindividualandcombined feature extraction methods is analyzed. Experimental results reveal that the HOG method achieves an accuracy of 78.99%, while the Texture Moments method yields 81.88%. Notably, the combination of these two methods enhances systemperformance, achieving the highest accuracy of 86.23%, representing a 4.65% improvement over the singlemethods. These findings underscore the efficacy of integrating HOG and Texture Moments with the Random Forest algorithm for automated batik pattern recognition.

Item Type:	Article
Uncontrolled Keywords:	Classification,Batik,HOG (Histogram ofOriented Gradients), Texture Moments, Random Forest
Subjects:	Engineering > Informatics Engineering Engineering
Divisions:	Faculty of Engineering > Informatics Engineering Study Program
Depositing User:	Wafiq Azizah
Date Deposited:	14 Aug 2025 04:21
Last Modified:	14 Aug 2025 04:21
URI:	http://eprints.umg.ac.id/id/eprint/14536

Actions (login required)

View Item