DETECTION AND PREDICTION OF CONCRETE CRACKS USING DEEP LEARNING-BASED IMAGE PROCESSING METHODS FOR QUALITY CONTROL

Abstract

One of the most critical defects in the quality control process of concrete elements is the detection of cracks. Furthermore, cracks are among the most significant indicators affecting concrete strength. Manual crack detection presents numerous disadvantages in terms of time, labor, cost, high error probability, and practical implementation challenges. Therefore, this study aims to detect cracks on concrete surfaces using vision techniques and automatically predict them using deep learning methods. Images classified as crack and non-crack, selected from a dataset obtained from the literature, were initially analyzed using Canny and Threshold methods. Subsequently, analyses were conducted using a novel voting ensemble model that combines deep learning models such as VGG16, ResNet50, Xception, and MobileNet. According to the results, cracks were successfully detected using vision techniques, and the proposed voting ensemble model achieved an accuracy value of 99.75% with a loss value of 0.00618. The findings demonstrate that automated quality control of concrete surfaces specifically for cracks can be performed with high accuracy.

Keywords

• Concrete Cracks
• Quality Control
• Vision Technics
• Pre-train Models
• Voting Ensemble Model

References

1. O. Khlifati, K. Baba, and B. A. Tayeh, "Survey of automated crack detection methods for asphalt and concrete structures," Innov. Infrastruct. Solut., vol. 9, no. 11, 2024, doi: 10.1007/s41062-024-01733-w.
2. N. Karimi, M. Mishra, and P. B. Lourenço, "Automated Surface Crack Detection in Historical Constructions with Various Materials Using Deep Learning-Based YOLO Network," International Journal of Architectural Heritage Conservation, Analysis, and Restoration, 2024, doi: 10.1080/15583058.2024.2376177.
3. M. G. Altun and A. H. Altun, "Beton Yüzey Çatlaklarının YOLOv8 Derin Öğrenme Algoritması ile Tespit Edilmesi," Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, vol. 39, no. 3, pp. 667–678, 2024, doi: 10.21605/cukurovaumfd.1560104.
4. S. M. Abualigah, A. F. Al-Naimi, G. Sachdeva, O. AlAmri, and L. Abualigah, "IDSDeep-CCD: intelligent decision support system based on deep learning for concrete cracks detection," Multimed Tools Appl, 2024, doi: 10.1007/s11042-024-18998-z.
5. B. Kim and S. Cho, "Automated Vision-Based Detection of Cracks on Concrete Surfaces Using a Deep Learning Technique," Sensors (Basel, Switzerland), vol. 18, no. 10, 2018, doi: 10.3390/s18103452.
6. R.-S. Rajadurai and S.-T. Kang, "Automated Vision-Based Crack Detection on Concrete Surfaces Using Deep Learning," Applied Sciences, vol. 11, no. 11, p. 5229, 2021, doi: 10.3390/app11115229.
7. Q. Zhou, S. Ding, G. Qing, and J. Hu, "UAV vision detection method for crane surface cracks based on Faster R-CNN and image segmentation," J Civil Struct Health Monit, vol. 12, no. 4, pp. 845–855, 2022, doi: 10.1007/s13349-022-00577-1.
8. C. Feng, H. Zhang, H. Wang, S. Wang, and Y. Li, "Automatic Pixel-Level Crack Detection on Dam Surface Using Deep Convolutional Network," Sensors (Basel, Switzerland), vol. 20, no. 7, 2020, doi: 10.3390/s20072069.

9. M. R. Bandi, L. N. Pasupuleti, T. Das, and S. Guchhait, "Deep learning based damage detection of concrete structures," Asian J Civ Eng, 2024, doi: 10.1007/s42107-024-01106-9.
10. F. Özgenel, Concrete Crack Images for Classification. Mendeley Data 2019, V2.
11. Y. Ding et al., "Innovative computer vision-based full-scale timber element cracks detection, stitching, and quantification," Structural Health Monitoring, 2024, doi: 10.1177/14759217241258682.
12. S.-M. Choi, H.-S. Cha, and S. Jiang, "Hybrid Data Augmentation for Enhanced Crack Detection in Building Construction," Buildings, vol. 14, no. 1929, pp. 1–32, 2024, doi: 10.3390/buildings14071929.
13. R. Kirthiga and S. Elavenil, "A survey on crack detection in concrete surface using image processing and machine learning," J Build Rehabil, vol. 9, no. 1, 2024, doi: 10.1007/s41024-023-00371-6.
14. S. Lee, M. Jeong, C.-S. Cho, J. Park, and S. Kwon, "Deep Learning-Based PC Member Crack Detection and Quality Inspection Support Technology for the Precise Construction of OSC Projects," Applied Sciences, vol. 12, no. 19, p. 9810, 2022, doi: 10.3390/app12199810.
15. F. Song, B. Liu, and G. Yuan, "Pixel‐Level Crack Identification for Bridge Concrete Structures Using Unmanned Aerial Vehicle Photography and Deep Learning," Structural Control and Health Monitoring, vol. 2024, no. 1, pp. 1–14, 2024, doi: 10.1155/2024/1299095.
16. F. Chollet, Ed., Xception: Deep Learning With Depthwise Separable Convolutions, 2017.
17. K. S. Bhalaji Kharthik et al., "Transfer learned deep feature based crack detection using support vector machine: a comparative study," Scientific reports, vol. 14, no. 1, p. 14517, 2024, doi: 10.1038/s41598-024-63767-5.
18. H. Polat, S. Alpergin, and M. S. Özerdem, "Beton çatlakların derin öğrenme tabanlı semantik segmentasyonunda kodlayıcı değişkenlerinin karşılaştırmalı analizi," DÜMF MD, 2024, doi: 10.24012/dumf.1465724.
19. A. Geron, Hands-on Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems,O’Reilly, CA. 2017.
20. I. Karatas and A. Budak, "Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity," ECAM, vol. 31, no. 3, pp. 1123–1144, 2024, doi: 10.1108/ECAM-08-2021-0692.
21. M. M. Hossain, M. B. Arefin, F. Akhtar, and J. Blake, “Combining state-of-the-art pre-trained deep learning models: A noble approach for skin cancer detection using max voting ensemble”. Diagnostics, 14(1), 89, 2023.
22. M. Mishra, V. Jain, S. K. Singh, and D. Maity, "Two-stage method based on the you only look once framework and image segmentation for crack detection in concrete structures," Archit. Struct. Constr., vol. 3, no. 4, pp. 429–446, 2023, doi: 10.1007/s44150-022-00060-x.
23. F. Sermet, I. Pachal, “Deep Learning-Based of Concrete Cracks Using Mobilenet Architectures,” Süni İntellekt: Nəzəriyyədən Praktikaya, 259, 2024.
24. A. Sevinç, F. Özyurt, “Detection of concrete surface cracks with deep learning architectures”. International Journal of Innovative Engineering Applications, 6(2), 2022, doi: 10.46460/ijiea.1098046