Improving Infrastructure Maintenance with Deep Learning for Crack Detection
DOI:
https://doi.org/10.14311/CEJ.2026.03.0028Keywords:
Infrastructure inspection, Deep learning, Crack detection, Convolutional neural network, Vision transformer, Support vector machineAbstract
In today’s era the importance of infrastructure maintenance continues to grow as the population of humanity and urbanization grows. The need of maintaining infrastructure from pavement and concrete continues to be a relevant topic. This study serves to investigate machine learning approaches from a variety of architectures that can assist with the detection of cracks in concrete and pavement. In this study the four proposed models (CNN with a Prewitt Operator for edge detection, CNNViT, CNNSVM, and R-CNN) provide insight on what approach works to detect cracking effectively, and what factors can affect the detection of cracking. These models are trained on three datasets, consisting of images of concrete, pavement, and both concrete and pavement, and are classified into positive and negative. A series of experiments, such as changing the optimizer from Adam to NAG and to Nadam, and data sample size from 6000, 8000, and 12000, were performed. For the CNNSVM model the kernel was changed from linear to RBF, and to Poly, as was the C value from 1 and 4. The base CNN model achieved accuracy of 97.83%, 85.61%, and 95.11%, CNNViT achieved 98.17%, 84.61%, and 95.81% accu racy, CNNSVM model was least accurate, while R-CNN model achieved 95.02%, 87.22%, and 91.16% accuracy for the three datasets, respectively. The proposed models achieved satisfactory results for crack detection in pavement and concrete. Being able to detect cracks automatically and effectively contributes to more cost-effective solutions by utilizing machine learning techniques.
Received: 10.04.2025
Received in revised form: 26.06.2026
Accepted: 09.08.2026
Downloads
References
M. Gavilan, D. Balcones, O. Marcos, D. F. Llorca, M. A. Sotelo, I. Parra, M. Ocana, P. Aliseda, P. Yarza, and A. Amırola, “Adaptive Road Crack Detection System by Pavement Classification,” Sensors, vol. 11, no. 10, pp. 9628–9657, Oct. 2011. [Online]. Available: https://www.mdpi.com/1424-8220/11/10/9628
J. Mobert, “Outlook for the german housing market 2024/2025: Regulatory uncertainty eases. first price rises. pricing soon to be completed,” Frankfurt am Main, Germany, July 2024, original in German published on July 8, 2024. Published in English on July 17, 2024. [Online]. Available: https://www.dbresearch.com
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, May 2017. [Online]. Available: https://dl.acm.org/doi/10.1145/3065386
D. Bhatt, C. Patel, H. Talsania, J. Patel, R. Vaghela, S. Pandya, K. Modi, and H. Ghayvat, “CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope,” Electronics, vol. 10, no. 20, p. 2470, Oct. 2021. [Online]. Available: https://www.mdpi.com/2079-9292/10/20/2470
M. Asghari Ilani, L. Amini, H. Karimi, and M. Shavali Kuhshuri, “CNN-based Labelled Crack Detection for Image Annotation,” May 2024. [Online]. Available: https://www.preprints.org/manuscript/202405. 1702/v1
Z. Alom, T. M. Taha, C. Yakopcic, S. Westberg, P. Sidike, and M. S. Nasrin, “The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches.”
A. F. Agarap, “An Architecture Combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for Image Classification,” Feb. 2019, arXiv:1712.03541 [cs]. [Online]. Available: http://arxiv.org/abs/1712.03541
O. Moutik, H. Sekkat, S. Tigani, A. Chehri, R. Saadane, T. A. Tchakoucht, and A. Paul, “Convolutional neural networks or vision transformers: Who will win the race for action recognitions in visual data?” vol. 23, no. 2, p. 734. [Online]. Available: https://www.mdpi.com/1424-8220/23/2/734
K. Team, “Keras documentation: Dropout layer.” [Online]. Available: https://keras.io/api/layers/regularization layers/dropout/
I. Kandel, M. Castelli, and A. Popoviˇ c, “Comparative Study of First Order Optimizers for Image Classification Using Convolutional Neural Networks on Histopathology Images,” Journal of Imaging, vol. 6, no. 9, p. 92, Sep. 2020. [Online]. Available: https: //www.mdpi.com/2313-433X/6/9/92
Mayank Sharma, “Concrete crack detection using the integration of convolutional neural network and support vector machine,” vol. 23, p. 1928, publisher: . [Online]. Available: http://doi.nrct.go.th/?page= resolve doi&resolve doi=10.14456/scitechasia.2018.11
M. A. Chandra and S. S. Bedi, “Survey on SVM and their application in image classification,” International Journal of Information Technology, vol. 13, no. 5, pp. 1–11, Oct. 2021. [Online]. Available: https://link.springer.com/10.1007/s41870-017-0080-1
D. Boswell, “Introduction to support vector machines.”
D. Tomar and S. Agarwal, “A comparison on multi-class classification methods based on least squares twin support vector machine,” vol. 81, pp. 131–147. [Online]. Available: https://linkinghub.elsevier. com/retrieve/pii/S0950705115000520
A. Kurani, P. Doshi, A. Vakharia, and M. Shah, “A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting,” vol. 10, no. 1, pp. 183–208. [Online]. Available: https://link.springer.com/10.1007/ s40745-021-00344-x
D. Jahed Armaghani, Y. Y. Ming, A. Salih Mohammed, E. Momeni, and H. Maizir, “Effect of SVM kernel functions on bearing capacity assessment of deep foundations,” vol. 7, no. 3. [Online]. Available: https://doi.org/10.22115/scce.2023.356959.1510
V. N. Vapnik, The Nature of Statistical Learning Theory, 2nd ed., ser. Statistics for Engineering and Information Science. New York, NY: Springer, 2010.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need.” [Online]. Available: http://arxiv.org/abs/1706.03762
S. Zuo, Y. Xiao, X. Chang, and X. Wang, “Vision transformers for dense prediction: A survey,” vol. 253, p. 109552. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S0950705122007821
J. Maur´ ıcio, I. Domingues, and J. Bernardino, “Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review,” Applied Sciences, vol. 13, no. 9, p. 5521, Apr. 2023. [Online]. Available: https://www.mdpi.com/2076-3417/13/9/5521
H. Fan, B. Xiong, K. Mangalam, Y. Li, Z. Yan, J. Malik, and C. Feichtenhofer, “Multiscale vision transformers.” [Online]. Available: http://arxiv.org/abs/2104.11227
H. Alshammari, K. Gasmi, I. Ben Ltaifa, M. Krichen, L. Ben Ammar, and M. A. Mahmood, “Olive disease classification based on vision transformer and CNN models,” vol. 2022, pp. 1–10. [Online]. Available: https://www.hindawi.com/journals/cin/2022/3998193/
M. Shahin, F. F. Chen, M. Maghanaki, A. Hosseinzadeh, N. Zand, and H. Khodadadi Koodiani, “Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm,” [42] P. Padmapoorani and S. Senthilkumar, “Application of Sensors, vol. 24, no. 10, p. 3247, May 2024. [Online]. Available: https://www.mdpi.com/1424-8220/24/10/3247
H. Kaveh and R. Alhajj, “Recent advances in crack detection technologies for structures: a survey of 2022-2023 literature,” Frontiers in Built Environment, vol. 10, p. 1321634, Jul. 2024. [Online]. Available: https://www.frontiersin.org/articles/10.3389/fbuil.2024.1321634/full
Y. Sun, Z. Sun, and W. Chen, “The evolution of object detection methods,” vol. 133, p. 108458. [Online]. Available: https://linkinghub. elsevier.com/retrieve/pii/S095219762400616X
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
P. Preethi and H. R. Mamatha, “Region-based convolutional neural network for segmenting text in epigraphical images,” vol. 1, no. 2, pp. 103–111. [Online]. Available: https://ojs.bonviewpress.com/index.php/ AIA/article/view/293
Q. Zou, Y. Cao, Q. Li, Q. Mao, and S. Wang, “CrackTree: Automatic crack detection from pavement images,” vol. 33, no. 3, pp. 227–238. [Online]. Available: https://linkinghub.elsevier.com/retrieve/ pii/S0167865511003795
A. Ismail, T. Rahmat, and S. Aliman, “CHEST x-RAY IMAGE CLASSIFICATION USING FASTER r-CNN,” vol. 4, no. 1, p. 225. [Online]. Available: https://mjoc.uitm.edu.my/main/index.php/journal/ 19-volume-4-1-2019/51-6095
N.-D. Hoang, “An artificial intelligence method for asphalt pavement pothole detection using least squares support vector machine and neural network with steerable filter-based feature extraction,” vol. 2018, no. 1, p. 7419058. [Online]. Available: https://onlinelibrary.wiley.com/doi/10. 1155/2018/7419058
S. S. N., K. S., and R. G, “Review and analysis of crack detection and classification techniques based on crack types,” vol. 13, no. 8, p. 6056. [Online]. Available: http://ripublication.com/ijaer18/ijaerv13n8 63.pdf
I.-H. Kim, H. Jeon, S.-C. Baek, W.-H. Hong, and H.-J. Jung, “Application of crack identification techniques for an aging concrete bridge inspection using an unmanned aerial vehicle,” Sensors, vol. 18, no. 6, p. 1881, June 2018. [Online]. Available: https: //doi.org/10.3390/s18061881
N.-D. Hoang, Q.-L. Nguyen, and X.-L. Tran, “Automatic detection of concrete spalling using piecewise linear stochastic gradient descent logistic regression and image texture analysis,” Complexity, vol. 2019, no. 1, p. 5910625, 2019.
L. Deng, H.-H. Chu, P. Shi, W. Wang, and X. Kong, “Region based CNN method with deformable modules for visually classifying concrete cracks,” vol. 10, no. 7, p. 2528. [Online]. Available: https://www.mdpi.com/2076-3417/10/7/2528
Q. Zhou, Z. Qu, and C. Cao, “Mixed pooling and richer attention feature fusion for crack detection,” vol. 145, pp. 96–102. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S016786552100060X
K. Hacıefendio˘ glu and H. B. Bas¸a˘ga, “Concrete road crack detection using deep learning-based faster r-CNN method,” vol. 46, no. 2, pp. 1621–1633. [Online]. Available: https://link.springer.com/10.1007/ s40996-021-00671-2
L. Ali, F. Alnajjar, H. A. Jassmi, M. Gocho, W. Khan, and M. A. Serhani, “Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures,” vol. 21, no. 5, p. 1688. [Online]. Available: https://www.mdpi.com/1424-8220/21/5/1688
V. P. Golding, Z. Gharineiat, H. S. Munawar, and F. Ullah, “Crack detection in concrete structures using deep learning,” vol. 14, no. 13, p. 8117. [Online]. Available: https://www.mdpi.com/2071-1050/14/13/ 8117
R. Ali, J. H. Chuah, M. S. A. Talip, N. Mokhtar, and M. A. Shoaib, “Structural crack detection using deep convolutional neural networks,” vol. 133, p. 103989. [Online]. Available: https://linkinghub.elsevier. com/retrieve/pii/S0926580521004404
E. Asadi Shamsabadi, C. Xu, A. S. Rao, T. Nguyen, T. Ngo, and D. Dias da Costa, “Vision transformer-based autonomous crack detection on asphalt and concrete surfaces,” vol. 140, p. 104316. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S0926580522001893
R. E. Philip, A. D. Andrushia, A. Nammalvar, B. G. A. Gurupatham, and K. Roy, “A comparative study on crack detection in concrete walls using transfer learning techniques,” vol. 7, no. 4, p. 169. [Online]. Available: https://www.mdpi.com/2504-477X/7/4/169
P. Padmapoorani and S. Senthilkumar, “Application machine learning for crack detection on concrete structures using CNN architecture,” vol. 28, no. 1, p. e20230010. [Online]. Available: http://www.scielo.br/scielo.php?script=sci arttext& pid=S1517-70762023000100233&tlng=en
M. Iraniparast, S. Ranjbar, M. Rahai, and F. Moghadas Nejad, “Surface concrete cracks detection and segmentation using transfer learning and multi-resolution image processing,” vol. 54, pp. 386 398. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/ S2352012423006653
D. P. Yadav, B. Sharma, S. Chauhan, and I. B. Dhaou, “Bridging convolutional neural networks and transformers for efficient crack detection in concrete building structures,” vol. 24, no. 13, p. 4257. [Online]. Available: https://www.mdpi.com/1424-8220/24/13/4257
M. N. A. B. G. Taj, N. Alruwais, H. M. Alshahrani, J. Vijayalakshmi, N. Shanmugapriya, and S. Jayaprakash, “Precision crack analysis in concrete structures using CNN, SVM, and KNN: a machine learning approach,” vol. 29, no. 4, p. e20240551. [Online]. Available: http://www.scielo.br/scielo.php?script=sci arttext& pid=S1517-70762024000400262&tlng=en
S. D. Nguyen, T. S. Tran, V. P. Tran, H. J. Lee, M. J. Piran, and V. P. Le, “Deep learning-based crack detection: A survey,” International Journal of Pavement Research and Technology, vol. 16, pp. 943–967, April 2023. [Online]. Available: https://doi.org/10.1007/s42947-022-00172-z
Z. Han, H. Chen, Y. Liu, Y. Li, Y. Du, and H. Zhang, “Vision-based crack detection of asphalt pavement using deep convolutional neural network,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, vol. 45, pp. 2047–2055, May 2021. [Online]. Available: https://doi.org/10.1007/s40996-021-00668-x
The roadway safety problem | US department of transportation. [Online]. Available: https://www.transportation.gov/NRSS/SafetyProblem
Surface crack detection. [Online]. Available: https://www.kaggle.com/ datasets/arunrk7/surface-crack-detection
K. S. Kristombu Baduge, S. Thilakarathna, J. S. Perera, G. Ruwanpathirana, L. Doyle, M. Duckett, J. Lee, J. Saenda, and P. Mendis, “Asphalt cracked and uncracked image dataset,” vol. 1, publisher: Mendeley Data. [Online]. Available: https://data.mendeley.com/datasets/88kdyyc73h/1
Concrete & pavement crack dataset. [Online]. Available: https://www. kaggle.com/datasets/oluwaseunad/concrete-and-pavement-crack-images
concrete crack image detection. [Online]. Available: https://kaggle.com/ code/gcdatkin/concrete-crack-image-detection
W. M. R. Wan Fadzli, A. Y. Dak, and T. R. Razak, “A survey on various edge detection techniques in image processing and applied disease detection,” Journal of Computing Research and Innovation, vol. 9, no. 2, pp. 23–32, 2024. [Online]. Available: https://doi.org/10.24191/jcrim.v9i2.415
V. Maksimovic, B. Jaksic, M. Milosevic, J. Todorovic, and L. Mosurovic, “Comparative Analysis of Edge Detection Operators Using a Threshold Estimation Approach on Medical Noisy Images with Different Complexities,” Sensors, vol. 25, no. 1, p. 87, Dec. 2024. [Online]. Available: https://www.mdpi.com/1424-8220/25/1/87
T. Nishikawa, J. Yoshida, T. Sugiyama, and Y. Fujino, “Concrete crack detection by multiple sequential image filtering,” Computer-Aided Civil and Infrastructure Engineering, vol. 27, no. 1, pp. 29–47, 2012.
I. W. R. Pinastawa, M. G. Pradana, and K. Khoironi, “Edge detection model performance using canny, prewitt and sobel in face detection,” Sinkron: jurnal dan penelitian teknik informatika, vol. 8, no. 2, pp. 623 631, 2024.
Y. Jiang, D. Pang, and C. Li, “A deep learning approach for fast detection and classification of concrete damage,” Automation in Construction, vol. 128, p. 103785, Aug. 2021. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S0926580521002363
H. Wan, L. Gao, M. Su, Q. Sun, and L. Huang, “Attention-based convolutional neural network for pavement crack detection,” Advances in Materials Science and Engineering, vol. 2021, pp. 1–13, 2021. [Online]. Available: https://doi.org/10.1155/2021/5520515
H. Agrawal and K. Desai, “CANNY EDGE DETECTION: A COMPREHENSIVE REVIEW,” International Journal of Technical Research & Science, vol. 9, no. Spl, pp. 27–35, Jun. 2024. [On line]. Available: https://ijtrs.com/uploaded paper/CANNY%20EDGE% 20DETECTION%20A%20COMPREHENSIVE%20REVIEW.pdf
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
