A Comprehensive Review of Deep Learning-Based Crack Detection Approaches
Open accessThe DOI matches its Crossref record; 131 of the 131 references it cites were found in a registry or an index.
Abstract
The application of deep architectures inspired by the fields of artificial intelligence and computer vision has made a significant impact on the task of crack detection. As the number of studies being published in this field is growing fast, it is important to categorize the studies at deeper levels. In this paper, a comprehensive literature review of deep learning-based crack detection studies and the contributions they have made to the field is presented. The studies are categorised according to the computer vision aspect and at deeper levels to facilitate exploring the studies that utilised similar approaches to address the crack detection problem. Moreover, the authors perform a comparison between the studies which use the same publicly available data sets, in order to find the most promising crack detection approaches. Critical future directions for research are proposed, based on these reviewed studies as well as on trends and developments in areas similar to the crack detection area.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



![Figure 4 Typical output of a deep learning-based crack detection approach based on the IC setting [23].](https://figures.cochat.ai/paper-figures/884370bb8eab47a7bf5a533a706fb8b6/a-comprehensive-review-of-deep-learning-based-crack-detection-approaches-figure-4.png)
![Figure 5 Typical output of a deep learning-based crack detection approach based on the OR setting [3].](https://figures.cochat.ai/paper-figures/a68b552f45b8433dbb4d38b78a7feeba/a-comprehensive-review-of-deep-learning-based-crack-detection-approaches-figure-5.png)
![Figure 6 Typical output of a deep learning-based crack detection approach based on the SS setting [74].](https://figures.cochat.ai/paper-figures/4c38d31cb4df404e8847277be2d3c870/a-comprehensive-review-of-deep-learning-based-crack-detection-approaches-figure-6.png)

Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“CNN’s processing of images can be roughly divided into three categories: image classification, object recognition, and semantic segmentation [100].”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [100]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Damage-sensitive feature extraction can be achieved through image processing techniques, ML, and DL [100], where DL can automatically extract features for image classification, object recognition, and semantic segmentation tasks.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [100]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“, VGG-16 [38], InceptionV3 [123], and ResNet [33]) as the backbone architectures in the encoder module was performed.”
BackgroundMethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 5×
“Gopalakrishnan et al. [37] utilised the pre-trained VGG-16 [38] architecture on ImageNet data set to extract features and inputted them into different classical machine learning algorithms to perform crack detection.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“R-CNN [47], Fast R-CNN [50], and faster R-CNN [51] are members of this family, and faster R-CNN has been the most popular in the crack detection area.”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“In [26], in addition to classification of crack type into five classes, inspired by AlexNet [34] and LeNet [35], four CNNs with different depths were considered and compared.”
MethodYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 7×
“YOLO [48], YOLO9000 [60], and YOLOv3 [61] are members in this family.”
BackgroundInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Research works printed but not linked: 3
- Cagle, R.F. (2003). Infrastructure Asset Management: An Emerging Direction, AACE International Transactions.
- Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press.
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Nets. arXiv.
Cited by
Hütten, N., Gomes, M. A., Hölken, F., Andricevic, K., Meyes, R., & Meisen, T. (2024) · Applied System Innovation · doi:10.3390/asi7010011 · Cited by 248
“Ali et al. [19], Ali et al. [20], Hamishebahar et al. [21], and Intisar et al. [22] studied DL-based approaches to crack detection.”
Jia, J., & Li, Y. (2023) · Sensors · doi:10.3390/s23218824 · Cited by 182
“Image-based SHM can obtain damage-sensitive features from images of DD. Damage-sensitive feature extraction can be achieved through image processing techniques, ML, and DL [100], where DL can automatically extract features for image classification, object recognition, and semantic segmentation tasks.”
MethodYuan, Q., Shi, Y., & Li, M. (2024) · Remote Sensing · doi:10.3390/rs16162910 · Cited by 158
Recent computer vision applications for pavement distress and condition assessment
Hakea, A. H. E., & Fakhr, M. W. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104664 · Cited by 112
Automatic surface crack detection using segmentation-based deep-learning approach
Joshi, D., Singh, T. P., & Sharma, G. (2022) · Engineering Fracture Mechanics · doi:10.1016/j.engfracmech.2022.108467 · Cited by 79
Visual Concrete Bridge Defect Classification and Detection Using Deep Learning: A Systematic Review
Amirkhani, D., Allili, M. S., Hebbache, L., Hammouche, N., & Lapointe, J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3365296 · Cited by 74
“Unlike other surveys that studied specific concrete defects such as cracks [24], [36], [37], [38], or domain-independent methods for defect detection [39], our paper provides a comprehensive review of the most studied bridge concrete defects in the literature.”
BackgroundIbragimov, E., Kim, Y., Lee, J. H., Cho, J., & Lee, J.-J. (2024) · Sensors · doi:10.3390/s24072333 · Cited by 66
“Deep learning approaches have been applied successfully in various tasks, including object detection, classification, and segmentation [14].”
MethodA controllable generative model for generating pavement crack images in complex scenes
Zhang, H., Qian, Z., Zhou, W., Min, Y., & Liu, P. (2024) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13171 · Cited by 45
Rathi, S., Mirajkar, O., Shukla, S., Deshmukh, L., & Dangare, L. (2024) · Indian Journal of Information Sources and Services · doi:10.51983/ijiss-2024.14.1.4003 · Cited by 49
Geetha, G. K., Yang, H.-J., & Sim, S. (2023) · Sensors · doi:10.3390/s23031419 · Cited by 39
“References [33,34] and references therein exhaustively reported the advancement of conventional machine-learning- and deep-learning (DL)-assisted computer vision for automated concrete crack detection.”
BackgroundData-driven approach for AI-based crack detection: techniques, challenges, and future scope
Chakurkar, P. S., Vora, D. R., Patil, S., Mishra, S., & Kotecha, K. V. (2023) · Frontiers in Sustainable Cities · doi:10.3389/frsc.2023.1253627 · Cited by 38
A survey on crack detection in concrete surface using image processing and machine learning
Kirthiga, R., & Elavenil, S. (2023) · Journal of Building Pathology and Rehabilitation · doi:10.1007/s41024-023-00371-6 · Cited by 43
“The pixel setting for each category varies, with the conceptual segmentation possessing more pixels to spot cracks on the concrete surfaces [7].”
InfluentialXu, W., Li, X., Ji, Y., Li, S., & Cui, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-69722-8 · Cited by 36
Loss function inversion for improved crack segmentation in steel bridges using a CNN framework
Kompanets, A., Duits, R., Pai, G., Leonetti, D., & Snijder, H. H. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105896 · Cited by 36
“However, the detection of cracks in steel has its own peculiarities, and despite the growing scientific interest in the field of automatic visual crack detection [21], up to the best knowledge of the authors, there is no publicly available dataset with images of cracks in steel bridges.”
Shi, T., & Luo, H. (2025) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2025.140793 · Cited by 31
Deep CNN-based concrete cracks identification and quantification using image processing techniques
Gonthina, M., Chamata, R., Duppalapudi, J., & Lute, V. (2022) · Asian Journal of Civil Engineering · doi:10.1007/s42107-022-00526-9 · Cited by 30
“Many methods have been established based on image processing techniques, including edge detection, Hough transform, image segmentation, identification and detection of feature points, the digital image correlation (DIC) method, and photogrammetry (Hamishebahar et al., 2022).”
MethodEgodawela, S., Gostar, A. K., Buddika, H. A. D. S., Dammika, A. J., Harischandra, N., Navaratnam, S., & Mahmoodian, M. (2024) · Sensors · doi:10.3390/s24061936 · Cited by 32
“Although the base CNN architectures embedded within object detectors generalize well in on-field settings, the region proposal networks used to produce box predictions generalize poorly due to being highly susceptible to overfitting to datasets [22].”
BackgroundA Road Crack Segmentation Method Based on Transformer and Multi-Scale Feature Fusion
Xu, Y., Xia, Y., Zhao, Q., Yang, K., & Li, Q. (2024) · Electronics · doi:10.3390/electronics13122257 · Cited by 30
Xiong, C., Zayed, T. M., Jiang, X., Alfalah, G., & Abdelkader, E. M. (2024) · Sensors · doi:10.3390/s24134288 · Cited by 28
“The advent of computer vision models has paved the way for automatic inspection technologies, offering enhanced efficiency and precision in contrast to manual measurements, which are susceptible to inaccuracies and subjectivity [14,15].”
BackgroundLei, Q., Zhong, J., Wang, C., & Li, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122552 · Cited by 26
CrackYOLO: Rural Pavement Distress Detection Model with Complex Scenarios
Li, Y., Sun, S., Wei-dong, S., Zhang, J., & Teng, Q. (2024) · Electronics · doi:10.3390/electronics13020312 · Cited by 24
CL-YOLOv8: Crack Detection Algorithm for Fair-Faced Walls Based on Deep Learning
Li, Q., Zhang, G., & Yang, P. (2024) · Applied Sciences · doi:10.3390/app14209421 · Cited by 26
Synthetic Data Generation Techniques for Enhancing Crack Detection in Railway Concrete Sleepers
Aldao, E., Fernández-Pardo, L., Veiga-López, F., González-deSantos, L. M., & González-Jorge, H. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6158 · Cited by 23
Wang, J., & Ueda, T. (2024) · Structural Concrete · doi:10.1002/suco.202400722 · Cited by 21
“8.”
Towards Robotic Marble Resin Application: Crack Detection on Marble Using Deep Learning
Vrochidou, Ε., Sidiropoulos, G. K., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., Sarafis, I. T., Kalpakis, V., & Stamkos, A. (2022) · Electronics · doi:10.3390/electronics11203289 · Cited by 22
Ruseruka, C., Mwakalonge, J., Comert, G., Siuhi, S., Ngeni, F., & Major, K. (2023) · Sustainability · doi:10.3390/su15086438 · Cited by 21
Popli, R., Kansal, I., Verma, J., Khullar, V., Kumar, R., & Sharma, A. (2023) · Sustainability · doi:10.3390/su15129314 · Cited by 24
An Investigation Into the Advancements of Edge-AI Capabilities for Structural Health Monitoring
Mishra, A., Gangisetti, G., & Khazanchi, D. (2024) · IEEE Access · doi:10.1109/access.2024.3365550 · Cited by 21
Surface Defect-Extended BIM Generation Leveraging UAV Images and Deep Learning
Yang, L., Liu, K., Ou, R., Qian, P., Wu, Y., Tian, Z., Zhu, C., Feng, S., & Yang, F. (2024) · Sensors · doi:10.3390/s24134151 · Cited by 25
“Currently, image processing and deep learning methods [13–15] are extensively used in object detection and semantic segmentation.”
MethodA review of image-based deep learning methods for crack detection
Pandey, V., & Mishra, S. S. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20729-x · Cited by 32
“To increase the accuracy of systems in this area, Hamishebahar et al., 2022 [154] used the standard ML algorithms like Random Forest (RM), support vector machine (SVMs) and neural network (NNs) to retrieve handmade characteristics.”
Modification and Evaluation of Attention-Based Deep Neural Network for Structural Crack Detection
Yuan, H., Jin, T., & Ye, X. (2023) · Sensors · doi:10.3390/s23146295 · Cited by 19
Weakly supervised crack segmentation using crack attention networks on concrete structures
Mishra, A., Gangisetti, G., Azam, S. E., & Khazanchi, D. (2024) · Structural Health Monitoring · doi:10.1177/14759217241228150 · Cited by 19
“Hamishebahar et al. 19 and Ali et al. 22 advocated for weakly supervised and unsupervised learning approaches to process automatic labeling and to facilitate minimum human intervention in the crack detection task.”
InfluentialVincens, B., Corres, E., & Muttoni, A. (2024) · Engineering Structures · doi:10.1016/j.engstruct.2024.118492 · Cited by 19
Efficient data dimensionality reduction method for improving road crack classification algorithms
Rodriguez-Lozano, F. J., Gámez, J. C. V., Palomares, J. M., & Olivares, J. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13014 · Cited by 18
“Approaches based on crack classification need to perform the detection task as well, but despite this fact, the number of proposals is lower than for solely crack detection ones (Hamishebahar et al., 2022).”
BackgroundVison Transformer-Based Automatic Crack Detection on Dam Surface
Zhou, J., Zhao, G., & Li, Y. (2024) · Water · doi:10.3390/w16101348 · Cited by 18
Application of Mask R-CNN and YOLOv8 Algorithms for Concrete Crack Detection
Choi, Y.-J., Bae, B., Han, T. H., & Ahn, J. (2024) · IEEE Access · doi:10.1109/access.2024.3469951 · Cited by 16
Wang, Y., & Tian, Y. (2022) · Journal of Engineering · doi:10.1155/2022/7733196 · Cited by 19
“,is limitation has been addressed using different filters and some of the researchers addressed this issue by introducing the mean and standard deviation values [56].”
MethodShojaei, D., Jafary, P., & Zhang, Z. (2024) · Electronics · doi:10.3390/electronics13224426 · Cited by 15
Fourier-Mixture of Experts YOLO for concrete crack segmentation with visual interpretability
Chang, H., Bassir, D., Barrios, A., & Chen, G. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106452 · Cited by 16
TrueDeep: A systematic approach of crack detection with less data
Pandey, R., & Achara, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122785 · Cited by 14
Crack Detection of Brown Rice Kernel Based on Optimized ResNet-18 Network
Wang, Z., Hu, Z., & Xiao, X. (2023) · IEEE Access · doi:10.1109/access.2023.3341350 · Cited by 14
“The results showed that the recognition accuracy of the ResNet-18 network was the highest at 85.20% [8], [9].”
BackgroundInfluentialEnhancing Road Crack Localization for Sustainable Road Safety Using HCTNet
Yadav, D. P., Sharma, B., Chauhan, S., Amin, F., & Abbasi, R. (2024) · Sustainability · doi:10.3390/su16114409 · Cited by 14
Wang, D., Zhang, R., Zhang, R., Nie, G., & Wang, W. P. (2024) · Journal of Building Engineering · doi:10.1016/j.jobe.2024.111315 · Cited by 22
Dong, S., Cao, J., Wang, Y., Ma, J., Kuang, Z., & Zhang, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ada786 · Cited by 13
“Image classification, object recognition, and pixel-level semantic segmentation [19] are three main categories into which deep learning-based crack detection techniques can be divided.”
Hu, M., Yue, N., & Groves, R. M. (2024) · Procedia Structural Integrity · doi:10.1016/j.prostr.2023.12.023 · Cited by 12
Altaf, A., Mehmood, A., Filograno, M. L., Alharbi, S. A., & Iqbal, J. (2025) · Buildings · doi:10.3390/buildings15183362 · Cited by 12
Image-Based Crack Detection Method for FPSO Module Support
Su, X. H., Jia, Z., Ma, G., Qu, C., Dai, T., & Ren, L. (2022) · Buildings · doi:10.3390/buildings12081147 · Cited by 12
Domain adversarial training for classification of cracking in images of concrete surfaces
Santos, B. O., Valença, J., Costeira, J. P., & Júlio, E. (2022) · AI in Civil Engineering · doi:10.1007/s43503-022-00008-6 · Cited by 12
Park, J., Kim, Y., Kim, S. S., Kim, K. Y., & Yun, T. S. (2023) · Rock Mechanics and Rock Engineering · doi:10.1007/s00603-023-03678-5 · Cited by 11
“Therefore, this study employed CNN, a deep learning model known for its outstanding performance in fracture segmentation (Hamishebahar et al. 2022; Kherad-mandi and Mehranfar 2022).”
Wang, J., Wang, Z., Wang, Y., & Li, Z. (2025) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-025-01020-x · Cited by 13
Optimizing CNN for pavement distress detection via edge-enhanced multi-scale feature fusion
Wang, J., Li, X., Xu, Y., Zhou, Z., Wu, W., & Li, Z. (2025) · PLoS ONE · doi:10.1371/journal.pone.0319299 · Cited by 10
Liu, S., Isobe, K., Si, J., Li, D., & Ren, D. (2025) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2025.143383 · Cited by 11
Intelligent detection of fine cracks on sleepers based on improved YOLOv5 model of cascade fusion
Ling, L., Xue, F., Zhang, J., Huan, Y., & Chen, F. (2023) · Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit · doi:10.1177/09544097231159707 · Cited by 10
“5 Image processing technology has been widely used in crack detection research, which generally including threshold segmentation and edge detection.”
MethodUncertainty quantification for a deep learning models for image-based crack segmentation
dos Santos, K. R. M., Chassignet, A. G. J., Pantoja-Rosero, B. G., Rezaie, A. H., Savary, O., & Beyer, K. (2024) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-024-00879-6 · Cited by 10
“Among them, semantic segmentation with convolutional neural networks (CNNs) is an excellent tool for extracting cracks from digital images with high accuracy [1].”
Flexi-YOLO: A lightweight method for road crack detection in complex environments
Yang, J., Tian, R., Zhou, Z., Tan, X., & He, P. (2025) · PLoS ONE · doi:10.1371/journal.pone.0325993 · Cited by 9
“Factors such as background noise, surface texture, lighting shadows, crack edges, and variations in crack shape, size, depth, and moisture often lead to false positives and missed detections, increasing the difficulty of detection [9].”
Paramanandham, N., Rajendiran, K., Poovathy, J. F. G., Premanand, Y. S., Mallichetty, S. R., & Kumar, P. (2023) · Sensors · doi:10.3390/s23062954 · Cited by 9
Intelligence Approach for Structural Monitoring via UAV-Artificial Intelligence-Based
Dangui, G., Hong, W., & Altabey, W. A. (2023) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc257844.2023.10293349 · Cited by 9
Meta-heuristic algorithms: an appropriate approach in crack detection
Ghannadiasl, A., & Ghaemifard, S. (2024) · Innovative Infrastructure Solutions · doi:10.1007/s41062-024-01583-6 · Cited by 9
Aliff, M., Hanisah, N. F., Nor, M. S. A. M., Hassan, S., Nurr, S. F., & Sani, N. S. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0131152 · Cited by 9
“Several detection techniques utilizing image processing with deep learning have previously been deployed by mounting cameras on ROVs to detect fractures in infrastructure such as walls and pipelines, but results can still vary due to ambient factors such as illumination [15].”
BackgroundCrack Severity Classification from Timber Cross-Sectional Images Using Convolutional Neural Network
Kato, S., Wada, N., Shiogai, K., Tamaki, T., Kagawa, T., Toyosaki, R., & Nobuhara, H. (2023) · Applied Sciences · doi:10.3390/app13031280 · Cited by 9
YOLOv8-Based Object Detection Model for Automated Bridge Crack Detection
AL-Qadri, M., Gao, P., Zhang, H., Chen, L., & Zhang, J. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251320388 · Cited by 8
Multi-temporal crack segmentation in concrete structures using deep learning approaches
Harb, S., Achanccaray, P., Maboudi, M., & Gerke, M. (2025) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-g-2025-341-2025 · Cited by 14
“According to Hamishe-bahar et al. (2022), pure segmentation architectures can be further divided into two fundamental types: encoder-decoder and non-encoder-decoder architectures.”
InfluentialDa, Y., Gao, Y., Li, Y., Ren, D., Liu, K., Brás, A., & Shaw, A. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106523 · Cited by 9
INTELLIGENT 3D CRACK RECONSTRUCTION USING CLOSE RANGE PHOTOGRAMMETRY IMAGERY
Majidi, S., Omidalizarandi, M., & Sharifi, M. A. (2023) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-4-w1-2022-443-2023 · Cited by 9
MLFF-InternImage: Pavement crack semantic segmentation model integrating multi-level fusion features
Li, G., Yang, J., Hong, J., & Liu, Y. (2024) · Measurement · doi:10.1016/j.measurement.2024.115686 · Cited by 9
Komi, D., Yoshida, D., & Kameyama, T. (2025) · Sensors · doi:10.3390/s25144325 · Cited by 7
“This technique has been widely used in patch-based deep learning models for crack detection, as it significantly improves the model’s ability to localize cracks near edges [19].”
Ren, X., & Liu, X. (2025) · Engineering Failure Analysis · doi:10.1016/j.engfailanal.2025.110057 · Cited by 9
Wang, J., Yang, Y., Wang, Z., Lv, L., & Ueda, T. (2026) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-025-01050-5 · Cited by 8
Hwang, S., Blay, K. B., Goodier, C. I., Gorse, C. A., & Cavalaro, S. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6572 · Cited by 6
Amirkhani, D., Allili, M. S., & Lapointe, J. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3591407 · Cited by 8
“The advent of machine learning (ML) methods, including support vector machines (SVMs) and random forests, combined with advanced feature engineering techniques, marked an improvement in crack segmentation [10], [11], [12].”
Machine Learning and Deep Learning to Analyze Material Durability
Monteiro, M., Andrade, M. S., & Guedes, R. M. (2025) · Journal of Materials Engineering and Performance · doi:10.1007/s11665-025-12732-y · Cited by 7
Experimental Study on the Azimuthal-Transmitting Transducer of Acoustic Logging
Lu, J., Men, B., & Che, X. (2023) · Sensors · doi:10.3390/s23063247 · Cited by 6
Daimari, E., Ratna, P. S., Mouli, C., & Madhurima, V. (2024) · The European Physical Journal E · doi:10.1140/epje/s10189-024-00453-4 · Cited by 6
“In general, crack detection studies can be categorized into three primary settings: image classification (IC), object recognition (OR), and semantic segmentation (SS) [35].”
Ruwanpathirana, G. P., Thilakarathna, S., & Baduge, S. K. (2025) · Case Studies in Construction Materials · doi:10.1016/j.cscm.2025.e04613 · Cited by 10
An Image-Based Hairline Crack Identification Method for Metal Parts
Hao, C., He, Y., Li, Y., Niu, X., & Wang, S. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3324689 · Cited by 12
“In recent years, image-based crack detection techniques have been extensively studied across diverse industries, such as architecture, highways, bridges, and dams [14], with limited research focusing on hairline cracks for metal parts.”
BackgroundCCT Net: A Dam Surface Crack Segmentation Model Based on CNN and Transformer
Ling, H., & Sun, F. (2025) · Infrastructures · doi:10.3390/infrastructures10090240 · Cited by 5
“These limitations make it difficult to achieve accurate and comprehensive assessment [3].”
Zhou, C., Dai, M., Wang, F., Dong, Y., Chen, X., & He, C. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07903-6 · Cited by 5
Unsupervised and noise-resilient crack detection in concrete and masonry via self-organizing maps
Sun, X., & Chang, P. (2026) · Engineering Structures · doi:10.1016/j.engstruct.2026.122130 · Cited by 5
A CNN ARCHITECTURE FOR DISCONTINUITY DETERMINATION OF ROCK MASSES WITH CLOSE RANGE IMAGES
Yalcin, I., Can, R., Kocaman, S., & Gökçeoğlu, C. (2022) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2022-1101-2022 · Cited by 5
Sattar, K. A., Abdel-Nasser, M., Ferik, S. E., & Taha, A. E. (2025) · Transportation research procedia · doi:10.1016/j.trpro.2025.03.105 · Cited by 5
A review of concrete bridge surface defect detection based on deep learning
Liao, Y., Huang, C.-Y., & Soliman, A. (2025) · Optoelectronics Letters · doi:10.1007/s11801-025-4116-7 · Cited by 6
Detection of Surface Defects Inside Concrete Pipelines Using Trained Model on JetRacer Kit
Mysiuk, R., Yuzevych, V., Mysiuk, I., Tyrkalo, Y., Pavlenchyk, A., & Dalyk, V. (2023) · IEEE International Conference on Electronics and Information Technologies (ELIT) · doi:10.1109/elit61488.2023.10310691 · Cited by 5
Kang, K.-S., Seo, J., & Ryu, H.-G. (2024) · Journal of Building Engineering · doi:10.1016/j.jobe.2024.110650 · Cited by 7
BERT-BiLSTM-BiGRU-CRF: Ensemble Multi Models Learning for Product Review Sentiment Analysis
Mouthami, K., Anandamurugan, S., & Ayyasamy, S. (2022) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca55336.2022.10009469 · Cited by 5
“3) Deep learning in sentiment analysis: Impart the system and play a vital role in text mining, natural language processing, sentiment analysis, etc. [10].”
BackgroundA Robust and Real-Time Hyper-Spectral Sensor-Fusion Model for Concrete Crack Segmentation
Steiner, M., Baumann, N., Lebovitz, L., & Magno, M. (2023) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas58821.2023.10254080 · Cited by 4
“Existing research primarily focuses on standard Red Green Blue (RGB) images [3, 8].”
BackgroundMethodCrack segmentation in roads using synthetic data and RGB-D data fusion
Marsh, B., & Wu, R. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104452 · Cited by 4
CrackScan: Enabling Intelligent Edge Inspection With UAVs for Structural Health Monitoring
Gonthina, S. S., Aditya, S. V. S., Teja, G. A., Das, D., & Sinha, A. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3610134 · Cited by 4
“The integration of deep learning models [8] not only enhances the speed and efficiency of crack detection but also significantly reduces the potential for errors and inaccuracies associated with traditional methods.”
Makkena, M., Lingamallu, G., Digavalli, V. H., Gudupalli, V. R., Manikandan, V. M., & Panchikkil, S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725066 · Cited by 4
“These measurements offer valuable insights into the size and spatial extent of detected cracks, aiding in comprehensive structural assessment [1].”
BackgroundAutomated Crack Analysis and Reporting in Civil Infrastructure using Generative AI
J, S. K. K., Nandini, K. L. A., Dharshan, S., Sowmya, V., & Bandaragoda, T. (2024) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon55916.2024.10905875 · Cited by 4
“Comprehensive reviews categorize deep learning-based crack detection methods by their computer vision aspects, comparing performances on publicly available datasets [10].”
Karballaeezadeh, N., Maaruof, A., Danial Mohammadzadeh, S., Zamani, S., & Mudabbiruddin, M. (2023) · IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI) · doi:10.1109/saci58269.2023.10158577 · Cited by 4
Fusion of Thermal and RGB Images for Automated Deep Learning Based Marble Crack Detection
Vrochidou, Ε., Sidiropoulos, G. K., Tsimperidis, I., Ouzounis, A. G., Sarafis, I. T., Kalpakis, V., Stamkos, A., & Papakostas, G. A. (2023) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot58121.2023.10174288 · Cited by 4
“Recent advancements in deep learning (DL) algorithms have gained considerable attention from both industry and academia towards automatic fault diagnosis [2].”
BackgroundSC-CrackSeg: A Real-time Shared Feature Pyramid Network for Crack Detection and Segmentation
Singha, T., Bergemann, M., Pham, D.-S., & Krishna, A. (2022) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta56598.2022.10034629 · Cited by 4
“Crack detection has been a growing area of research in recent years [18].”
BackgroundDesai, M. K., Buch, S. H., & Desai, J. H. (2024) · Journal of Image Processing and Intelligent Remote Sensing · doi:10.55529/jipirs.46.19.28 · Cited by 3
Çapunaman, Ö. B., Mohseni, A., Dombrovskij, D., Yin, K., Gürsoy, B., & Mylo, M. D. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103187 · Cited by 5
Kim, D., Gerstberger, U., Asli, M., & Höschler, K. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.108864 · Cited by 4
Sait, A. R. W., Sankaranarayanan, S., & Yu, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-40359-z · Cited by 3
“Recently, convolutional neural networks (CNNs) and other deep learning (DL) techniques have been employed in classifying SC 9–11 .”
Li, Y. (2026) · Journal of Engineering and Applied Science · doi:10.1186/s44147-026-00956-1 · Cited by 3
Liu, X., Ding, Y., Xu, F., Yang, K., & Geng, F. (2026) · Engineering Structures · doi:10.1016/j.engstruct.2026.122602 · Cited by 3
Bai, Y., Quan, W., Shi, X., Yan, Z. H., & Yuan, G. (2026) · Remote Sensing · doi:10.3390/rs18111806 · Cited by 3
Segmentation of crack disaster images based on feature extraction enhancement and multi-scale fusion
Wang, L., Wu, G., Tossou, A. I. H. C. F., Liang, Z., & Xu, J. (2024) · Earth Science Informatics · doi:10.1007/s12145-024-01511-3 · Cited by 3
“Hamishebahar et al. (2022) thoroughly analyzed and reviewed deep learning in crack detection.”
Metadata
- Authors
- Hamishebahar, Y., Guan, H., So, S., & Jo, J.
- Affiliations
- Griffith University (AU)
- Corresponding author
- Hamishebahar, Younes
- Guan, Hong
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2022-01-27
- Volume
- 12
- Issue
- 3
- Pages
- 1374
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4210629389
- Cited by
- 188
- References
- 115
- Citations by year
- 2026: 37 · 2025: 59 · 2024: 47 · 2023: 31 · 2022: 14
- FWCI
- 16.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Griffith Research Online (submittedVersion, cc-by)
- Topics
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- crack detection, deep learning, computer vision, image-based defect detection, benchmark dataset, future research directions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.