Lightweight Alternative Machine Learning Model for Automating Concrete Crack Image Classification

International Concrete Abstracts Portal

The International Concrete Abstracts Portal is an ACI led collaboration with leading technical organizations from within the international concrete industry and offers the most comprehensive collection of published concrete abstracts.

  


Title: Lightweight Alternative Machine Learning Model for Automating Concrete Crack Image Classification

Author(s): Sang Min Lee, Hyeon-Sik Choi, Chanho Kim, and Thomas H.-K. Kang

Publication: Structural Journal

Volume: 122

Issue: 5

Appears on pages(s): 97-106

Keywords: concrete crack image; convolutional neural network (CNN); histogram of oriented gradients (HOG); local binary patterns (LBP); random forest (RF)

DOI: 10.14359/51746755

Date: 9/1/2025

Abstract:
In this study, the challenge of automating concrete crack image classification by developing a lightweight machine learning model that balances accuracy with computational efficiency was addressed. Traditional deep learning models, while accurate, suffer from high computational demands, limiting their practicality in on-site applications. This study’s approach used the random forest (RF) classifier combined with histogram of oriented gradients (HOG) and local binary patterns (LBP) for feature extraction, offering a more feasible alternative for real-time structural health monitoring. Comparative analysis with the convolutional neural network (CNN) model highlights this model’s significantly reduced size and inference times, with only a marginal compromise in accuracy. The results demonstrated that the RF models, particularly RF with LBP, are well-suited for integration into resource-constrained environments, paving the way for their deployment in portable, on-site diagnostic systems in civil engineering. This study contributed a novel perspective to the field, emphasizing the importance of efficient machine learning solutions in practical applications of structural health monitoring.

Related References:

Ali, L.; Alnajjar, F.; Jassmi, H. A.; Gocho, M.; Khan, W.; and Serhani, M. A., 2021, “Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures,” Sensors, V. 21, No. 5, p. 1688. doi: 10.3390/s21051688

Dais, D.; Bal, I. E.; Smyrou, E.; and Sarhosis, V., 2021, “Automatic Crack Classification and Segmentation on Masonry Surfaces Using Convolutional Neural Networks and Transfer Learning,” Automation in Construction, V. 125, p. 103606. doi: 10.1016/j.autcon.2021.103606

Fu, R.; Cao, M.; Novak, D.; Qian, X.; and Alkayem, N. F., 2023, “Extended Efficient Convolutional Neural Network for Concrete Crack Detection with Illustrated Merits,” Automation in Construction, V. 156, p. 105098. doi: 10.1016/j.autcon.2023.105098

Huyan, J.; Ma, T.; Li, W.; Yang, H.; and Xu, Z., 2022, “Pixelwise Asphalt Concrete Pavement Crack Detection via Deep Learning-Based Semantic Segmentation Method,” Structural Control and Health Monitoring, V. 29, No. 8, p. e2974. doi: 10.1002/stc.2974

Islam, M. M.; Hossain, M. B.; Akhtar, M. N.; Moni, M. A.; and Hasan, K. F., 2022, “CNN Based on Transfer Learning Models Using Data Augmentation and Transformation for Detection of Concrete Cracks,” Algorithms, V. 15, No. 8, p. 287. doi: 10.3390/a15080287

Kim, H.; Ahn, E.; Shin, M.; and Sim, S.-H., 2019, “Crack and Noncrack Classification from Concrete Surface Images Using Machine Learning,” Structural Health Monitoring, V. 18, No. 3, pp. 725-738. doi: 10.1177/1475921718768747

Maalej, M.; Cherif, R.; Yaddaden, Y.; and Khoumsi, A., 2022, “Automatic Crack Detection on Concrete Structure Using a Deep Convolutional Neural Network and Transfer Learning,” 2022 International Conference on Advanced Electrical Engineering (ICAEE), Constantine, Algeria. doi: 10.1109/ICAEE53772.2022.9962029

Meng, X., 2021, “Concrete Crack Detection Algorithm Based on Deep Residual Neural Networks,” Scientific Programming, V. 2021, p. 3137083. doi: 10.1155/2021/3137083

Özgenel, Ç. F., 2018, “Concrete Crack Images for Classification,” Mendeley Data. doi: 10.17632/5y9wdsg2zt.1

Rajadurai, R.-S., and Kang, S.-T., 2021, “Automated Vision-Based Crack Detection on Concrete Surfaces Using Deep Learning,” Applied Sciences, V. 11, No. 11, p. 5229. doi: 10.3390/app11115229

Yu, Y.; Rashidi, M.; Samali, B.; Mohammadi, M.; Nguyen, T. N.; and Zhou, X., 2022, “Crack Detection of Concrete Structures Using Deep Convolutional Neural Networks Optimized by Enhanced Chicken Swarm Algorithm,” Structural Health Monitoring, V. 21, No. 5, pp. 1-15. doi: 10.1177/14759217211053546

Zhang, L.; Yang, F.; Zhang, Y. D.; and Zhu, Y. J., 2016, “Road Crack Detection Using Deep Convolutional Neural Network,” 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, pp. 3708-3712. doi: 10.1109/ICIP.2016.7533052

Zhou, Z.; Zhang, J.; and Gong, C., 2022, “Automatic Detection Method of Tunnel Lining Multi-Defects via an Enhanced You Only Look Once Network,” Computer-Aided Civil and Infrastructure Engineering, V. 37, No. 6, pp. 762-780. doi: 10.1111/mice.12836


ALSO AVAILABLE IN:

Electronic Structural Journal



  

Edit Module Settings to define Page Content Reviewer