Comparison of Road Damage Classification Accuracy Based on Grayscale Bit Depth Using GLCM Feature Extraction and Backpropagation Neural Network

Muhamad Amirul Akbar; Gasim; Nazori Suhandi

doi:10.59934/jaiea.v5i2.2088

Authors

Muhamad Amirul Akbar Universitas Indo Global Mandiri Palembang
Gasim Universitas Indo Global Mandiri Palembang
Nazori Suhandi Universitas Indo Global Mandiri Palembang

DOI:

https://doi.org/10.59934/jaiea.v5i2.2088

Keywords:

artificial neural network; GLCM; grayscale bit depth; image processing; road damage detection

Abstract

Road surface damage such as cracks, potholes, and patches can reduce driving comfort and threaten road user safety. Manual road inspection is time-consuming and inefficient, especially for large urban areas. This study proposes an image-based approach to classify road damage types using Gray Level Co-occurrence Matrix (GLCM) feature extraction and a backpropagation artificial neural network. Road images were captured directly in Palembang City using a smartphone camera and converted into grayscale images with five different bit depths: 4-bit, 5-bit, 6-bit, 7-bit, and 8-bit. Texture features including contrast, correlation, energy, and homogeneity were extracted using GLCM and used as inputs to the neural network classifier. Experimental results show that higher grayscale bit depth produces better classification accuracy, with 8-bit grayscale achieving the highest performance compared to lower bit depths. The results confirm that grayscale resolution significantly affects texture representation and classification accuracy. This approach can support automated and efficient road damage detection systems.

Downloads

Download data is not yet available.

References

R. M. Haralick, K. Shanmugam, dan I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, hlm. 610–621, 1973.

H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, dan H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Computer-Aided Civil and Infrastructure Engineering, vol. 33, no. 12, hlm. 1127–1141, 2018, doi: 10.1111/mice.12387.

T. Maeda et al., “Road damage detection using deep neural networks with images captured through a smartphone,” arXiv preprint, arXiv:1801.09454, 2018.

M. Fikri dan A. A. Sarira, “Analisis tingkat kerusakan jalan dengan metode Pavement Condition Index (Studi kasus Jalan Poros Latuppa–Bonglo),” Jurnal Ilmiah Ecosystem, vol. 23, no. 2, hlm. 345–351, 2023.

J. Jumadi, Y. Yupianti, dan D. Sartika, “Pengolahan citra digital untuk identifikasi objek menggunakan metode Hierarchical Agglomerative Clustering,” JST (Jurnal Sains dan Teknologi), vol. 10, no. 2, hlm. 148–156, 2021, doi: 10.23887/jstundiksha.v10i2.33636.

A. Mahardika, Y. A. Sari, dan C. Dewi, “Sistem temu kembali citra lubang jalan aspal berdasarkan tingkat kerusakan menggunakan ekstraksi fitur Gray Level Co-occurrence Matrix (GLCM),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 2, no. 7, hlm. 3811–3821, 2018.

I. Mandaya, “Pemanfaatan Unmanned Aerial Vehicle (UAV) untuk identifikasi dan klasifikasi jenis-jenis kerusakan jalan,” Jurnal Teknik Sipil, vol. 14, no. 3, hlm. 162–172, 2020.

D. I. Mulyana dan I. Wahyudi, “Deteksi kerusakan jalan berdasarkan citra digital menggunakan Convolutional Neural Network (CNN),” Jurnal Informatika dan Sistem Informasi, vol. 6, no. 1, hlm. 294–302, 2025.

P. Pramudiya, C. Asyraq, A. Kadafi, dan R. P. Sardika, “Analisis gambar menggunakan metode grayscale dan HSV (Hue, Saturation, Value),” Jurnal Sistem Informasi, Teknologi Informasi, dan Komputer, vol. 14, no. 3, hlm. 174–180, 2024

R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, 1973.

T. Maeda et al., “Road damage detection using deep neural networks with images captured through a smartphone,” arXiv preprint arXiv:1801.09454, 2018.

D. I. Mulyana and I. Wahyudi, “Road damage detection based on digital image using convolutional neural network,” Journal of Artificial Intelligence and Engineering Applications, vol. 4, no. 2, pp. 45–52, 2024.

A. Mahardika, Y. A. Sari, and C. Dewi, “Image retrieval system for a