Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Algoritme Jurnal Mahasiswa Teknik Informatika

Klasifikasi Penggunaan Helm pada Citra Pengendara Sepeda Motor Menggunakan K-Means Clustering dan GLCM Antoni, Antoni; Ramadhanu, Agung
Jurnal Algoritme Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.10921

Abstract

The safety of motorcycle riders is a critical issue, particularly in countries with high traffic accident rates. In Indonesia, motorcycles make up the majority of personal vehicles, with over 130 million units as of June 2023, but many riders fail to comply with helmet usage regulations. Helmets significantly reduce the risk of fatal head injuries, yet the compliance rate remains low. To address this issue, an image classification system for motorcycle riders using helmets is proposed, leveraging image processing techniques and machine learning. By leveraging the K-Means Clustering algorithm, the system segments motorcycle images into two categories: riders with helmets and those without. The images are pre-processed, converted from RGB to LAB color space, and K-Means clustering is used to segment background and object areas. Feature extraction is applied using GLCM (Gray-Level Co-occurrence Matrix) to identify key characteristics such as texture and shape. The system compares the extracted features using Euclidean distance to classify whether a rider is wearing a helmet. Results show an accuracy rate of 94% in classifying helmet usage from 50 test images. This method can serve as an efficient and cost-effective alternative to more computationally intensive techniques like deep learning, with potential for real-time traffic surveillance applications.