International Journal of Advanced Technology and Engineering Exploration ISSN (Print): 2394-5443    ISSN (Online): 2394-7454 Volume-13 Issue-137 April-2026
  1. 4037
    Citations
  2. 2.7
    CiteScore
Concrete crack classification using deep feature fusion and XGBoost for structural health monitoring

Kavita Bodke1, S. G. Bhirud2 and K. K. Sangle3

Department of Computer Engineering,Veermata Jijabai Technological Institute,Mumbai, 400019,India1
Vice-Chancellor,COEP Tech. University,Pune, 411005,India2
Department of Structural Engineering,Veermata Jijabai Technological Institute,Mumbai, 400019,India3
Corresponding Author : Kavita Bodke

Recieved : 04-August-2025; Revised : 23-April-2026; Accepted : 24-April-2026

Abstract

Automated crack detection is a vital component of structural health monitoring (SHM) for civil infrastructure. Conventional methods and standalone deep learning (DL) systems often struggle to handle the wide variability in concrete crack formations, resulting in unreliable performance. This study presents a robust and scalable solution by integrating the strengths of multiple models. A novel methodology for concrete crack classification is proposed, which combines an ensemble of 14 pre-trained convolutional neural networks (CNNs), including residual network models (ResNet50V2, ResNet101V2), MobileNet variants (MobileNetV2, MobileNetV3Large, MobileNetV3Small), EfficientNet models (EfficientNetB0, EfficientNetB1, EfficientNetB2), visual geometry group models (VGG16, VGG19), InceptionV3, DenseNet121, DenseNet169, and Xception. These models are employed to extract a diverse set of structural features from concrete crack images. The extracted features are then fused into a comprehensive high-dimensional feature vector, which is used as input to an optimized extreme gradient boosting (XGBoost) classifier. The classifier is trained and validated using a 3-fold stratified cross-validation strategy. The proposed methodology achieves an average cross-validation accuracy of 94.38% and a final testing accuracy of 96.25%. The results demonstrate the effectiveness of the multi-model feature fusion approach. The proposed framework offers a promising solution for automated crack assessment, contributing to more efficient and accurate management of civil infrastructure.

Keywords

Structural health monitoring (SHM), Concrete crack detection, Convolutional neural networks (CNNs), Feature fusion, Extreme gradient boosting (XGBoost), Deep learning ensemble.

Cite this article

Bodke K, Bhirud SG, Sangle KK. Concrete crack classification using deep feature fusion and XGBoost for structural health monitoring. International Journal of Advanced Technology and Engineering Exploration. 2026;13(137):461-473. DOI : 10.19101/IJATEE.2025.121221084

References
[1]
Khan MZ, Shahzadi M, Khan A, Ali U, Hassan MA, Hussain M. Review on crack detection in civil infrastructure using structural health monitoring and machine learning techniques. Innovative Infrastructure Solutions. 2025; 10(8):348.
[Crossref] [Google Scholar]
[2]
Azimi M, Eslamlou AD, Pekcan G. Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors. 2020; 20(10):1-34.
[Crossref] [Google Scholar]
[3]
Flah M, Nunez I, Ben CW, Nehdi ML. Machine learning algorithms in civil structural health monitoring: a systematic review. Archives of Computational Methods in Engineering. 2021; 28(4):2621-43.
[Crossref] [Google Scholar]
[4]
Chakurkar PS, Vora D, Patil S, Mishra S, Kotecha K. Data-driven approach for AI-based crack detection: techniques, challenges, and future scope. Frontiers in Sustainable Cities. 2023; 5:1-28.
[Crossref] [Google Scholar]
[5]
Yuan Q, Shi Y, Li M. A review of computer vision-based crack detection methods in civil infrastructure: progress and challenges. Remote Sensing. 2024; 16(16):1-34.
[Crossref] [Google Scholar]
[6]
Mohan A, Poobal S. Crack detection using image processing: a critical review and analysis. Alexandria Engineering Journal. 2018; 57(2):787-98.
[Crossref] [Google Scholar]
[7]
Liu YF, Fan JS, Nie JG, Kong SY, Qi Y. Review and prospect of digital-image-based crack detection of structure surface. China Civil Engineering Journal. 2021; 54(6):79-98.
[Google Scholar]
[8]
Canny J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2009; 27(6):679-98.
[Crossref] [Google Scholar]
[9]
Otsu N. A threshold selection method from gray-level histograms. Automatica. 1975; 11:285-96.
[Google Scholar]
[10]
Sezgin M, Sankur BL. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 2004; 13(1):146-68.
[Crossref] [Google Scholar]
[11]
Pal M, Palevičius P, Landauskas M, Orinaitė U, Timofejeva I, Ragulskis M. An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows. Applied Sciences. 2021; 11(23):1-14.
[Crossref] [Google Scholar]
[12]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436-44.
[Crossref] [Google Scholar]
[13]
Li G, Ma B, He S, Ren X, Liu Q. Automatic tunnel crack detection based on u-net and a convolutional neural network with alternately updated clique. Sensors. 2020; 20(3):1-23.
[Crossref] [Google Scholar]
[14]
Liu Z, Cao Y, Wang Y, Wang W. Computer vision-based concrete crack detection using U-net fully convolutional networks. Automation in Construction. 2019; 104:129-39.
[Crossref] [Google Scholar]
[15]
Dorafshan S, Thomas RJ, Maguire M. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Construction and Building Materials. 2018; 186:1031-45.
[Crossref] [Google Scholar]
[16]
Hamishebahar Y, Guan H, So S, Jo J. A comprehensive review of deep learning-based crack detection approaches. Applied Sciences. 2022; 12(3):1-24.
[Crossref] [Google Scholar]
[17]
Ali R, Chuah JH, Talip MS, Mokhtar N, Shoaib MA. Structural crack detection using deep convolutional neural networks. Automation in Construction. 2022; 133:103989.
[Crossref] [Google Scholar]
[18]
Fan CL. Detection of multidamage to reinforced concrete using support vector machine‐based clustering from digital images. Structural Control and Health Monitoring. 2021; 28(12):e2841.
[Crossref] [Google Scholar]
[19]
Mazni M, Husain AR, Shapiai MI, Ibrahim IS, Anggara DW, Zulkifli R. An investigation into real-time surface crack classification and measurement for structural health monitoring using transfer learning convolutional neural networks and Otsu method. Alexandria Engineering Journal. 2024; 92:310-20.
[Crossref] [Google Scholar]
[20]
Meng S, Gao Z, Zhou Y, He B, Djerrad A. Real‐time automatic crack detection method based on drone. Computer‐Aided Civil and Infrastructure Engineering. 2023; 38(7):849-72.
[Crossref] [Google Scholar]
[21]
Humpe A. Bridge inspection with an off-the-shelf 360 camera drone. Drones. 2020; 4(4):1-23.
[Crossref] [Google Scholar]
[22]
Numan M. Advancements in structural health monitoring: a review of machine learning approaches for damage detection and assessment. International Journal for Computational Civil and Structural Engineering. 2024; 20(1):124-42.
[Google Scholar]
[23]
Birgani SA, Zadeh SS, Davari DD, Ostovar A. Deep learning applications for analysing concrete surface cracks. International Journal of Applied Data Science in Engineering and Health. 2024; 1(2):69-84.
[Google Scholar]
[24]
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-8). IEEE.
[Google Scholar]
[25]
Yan Z, Zhang H, Piramuthu R, Jagadeesh V, Decoste D, Di W, et al. HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In proceedings of the international conference on computer vision 2015 (pp. 2740-8). IEEE.
[Crossref] [Google Scholar]
[26]
Zhang X, Zhou X, Lin M, Sun J. Shufflenet: an extremely efficient convolutional neural network for mobile devices. In proceedings of the conference on computer vision and pattern recognition 2018 (pp. 6848-56). IEEE
[Crossref] [Google Scholar]
[27]
Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In international conference on machine learning 2019 (pp. 6105-14). PMLR.
[Google Scholar]
[28]
Sohaib M, Jamil S, Kim JM. An ensemble approach for robust automated crack detection and segmentation in concrete structures. Sensors. 2024; 24(1):1-18.
[Crossref] [Google Scholar]
[29]
Krishnan SS, Karuppan MN, Khadidos AO, Khadidos AO, Selvarajan S, Tandon S, et al. Comparative analysis of deep learning models for crack detection in buildings. Scientific Reports. 2025; 15(1):1-33.
[Crossref] [Google Scholar]
[30]
Alshawabkeh S, Wu L, Dong D, Cheng Y, Li L. A hybrid approach for pavement crack detection using mask R-CNN and vision transformer model. Computers, Materials, & Continua. 2025; 82(1):561-77.
[Crossref] [Google Scholar]
[31]
Fan CL. Evaluation model for crack detection with deep learning: improved confusion matrix based on linear features. Journal of Construction Engineering and Management. 2025; 151(3):04024210.
[Crossref] [Google Scholar]
[32]
Pham MV, Ha YS, Kim YT. Automatic detection and measurement of ground crack propagation using deep learning networks and an image processing technique. Measurement. 2023; 215:112832.
[Crossref] [Google Scholar]
[33]
Laxman KC, Tabassum N, Ai L, Cole C, Ziehl P. Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning. Construction and Building Materials. 2023; 370:130709.
[Crossref] [Google Scholar]
[34]
Flah M, Suleiman AR, Nehdi ML. Classification and quantification of cracks in concrete structures using deep learning image-based techniques. Cement and Concrete Composites. 2020; 114:103781.
[Crossref] [Google Scholar]
[35]
Liang S, Jianchun X, Xun Z. An extraction and classification algorithm for concrete cracks based on machine vision. IEEE Access. 2018; 6:45051-61.
[Crossref] [Google Scholar]
[36]
Ashraf A, Sophian A, Bawono AA. Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms. Construction Materials. 2024; 4(4):655-75.
[Crossref] [Google Scholar]
[37]
Jahanshahi MR, Masri SF, Padgett CW, Sukhatme GS. An innovative methodology for detection and quantification of cracks through incorporation of depth perception. Machine Vision and Applications. 2013; 24(2):227-41.
[Crossref] [Google Scholar]
[38]
Golding VP, Gharineiat Z, Munawar HS, Ullah F. Crack detection in concrete structures using deep learning. Sustainability. 2022; 14(13):1-25.
[Crossref] [Google Scholar]
[39]
Qayyum W, Ehtisham R, Bahrami A, Mir J, Khan QU, Ahmad A, et al. Predicting characteristics of cracks in concrete structure using convolutional neural network and image processing. Frontiers in Materials. 2023; 10:1210543.
[Crossref] [Google Scholar]
[40]
Özgenel ÇF. Concrete crack images for classification. Mendeley Data. 2019.
[Google Scholar]