{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:55:37Z","timestamp":1775667337374,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSERC (National Sciences and Engineering Research Council of Canada)","award":["ALLRP 555258-20"],"award-info":[{"award-number":["ALLRP 555258-20"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Periodical vision-based inspection is a principal form of structural health monitoring (SHM) technique. Over the last decades, vision-based artificial intelligence (AI) has successfully facilitated an effortless inspection system owing to its exceptional ability of accuracy of defects\u2019 pattern recognition. However, most deep learning (DL)-based methods detect one specific type of defect, whereas DL has a high proficiency in multiple object detection. This study developed a dataset of two types of defects, i.e., concrete crack and spalling, and applied various pre-built convolutional neural network (CNN) models, i.e., VGG-19, ResNet-50, InceptionV3, Xception, and MobileNetV2 to classify these concrete defects. The dataset developed for this study has one of the largest collections of original images of concrete crack and spalling and avoided the augmentation process to replicate a more real-world condition, which makes the dataset one of a kind. Moreover, a detailed sensitivity analysis of hyper-parameters (i.e., optimizers, learning rate) was conducted to compare the classification models\u2019 performance and identify the optimal image classification condition for the best-performed CNN model. After analyzing all the models, InceptionV3 outperformed all the other models with an accuracy of 91%, precision of 83%, and recall of 100%. The InceptionV3 model performed best with optimizer stochastic gradient descent (SGD) and a learning rate of 0.001.<\/jats:p>","DOI":"10.3390\/s22228714","type":"journal-article","created":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T04:30:52Z","timestamp":1668400252000},"page":"8714","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Performance Comparison of Multiple Convolutional Neural Networks for Concrete Defects Classification"],"prefix":"10.3390","volume":"22","author":[{"given":"Palisa","family":"Arafin","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}]},{"given":"Anas","family":"Issa","sequence":"additional","affiliation":[{"name":"Civil and Environmental Engineering Department, United Arab Emirates University, Al Ain P.O. Box 17551, Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9840-3438","authenticated-orcid":false,"given":"A. H. M. Muntasir","family":"Billah","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shin, H.K., Ahn, Y.H., Lee, S.H., and Kim, H.Y. (2020). Automatic concrete damage recognition using multi-level attention convolutional neural network. Materials, 13.","DOI":"10.3390\/ma13235549"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"134602","DOI":"10.1109\/ACCESS.2020.3011106","article-title":"Automatic crack detection and measurement of concrete structure using convolutional encoder-decoder network","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1061\/(ASCE)0887-3801(2003)17:4(264)","article-title":"Real-time image thresholding based on sample space reduction and interpolation approach","volume":"17","author":"Cheng","year":"2003","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1111\/j.1467-8667.2010.00674.x","article-title":"Beamlet transform-based technique for pavement crack detection and classification","volume":"25","author":"Ying","year":"2010","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s00138-009-0244-5","article-title":"A robust automatic crack detection method from noisy concrete surfaces","volume":"22","author":"Fujita","year":"2011","journal-title":"Mach. Vis. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1111\/j.1467-8667.2011.00716.x","article-title":"Concrete crack detection by multiple sequential image filtering","volume":"27","author":"Nishikawa","year":"2012","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1111\/j.1467-8667.2006.00445.x","article-title":"Segmentation of pipe images for crack detection in buried sewers","volume":"21","author":"Iyer","year":"2006","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s11265-013-0813-8","article-title":"An automatic approach for accurate edge detection of concrete crack utilizing 2D geometric features of crack","volume":"77","author":"Nguyen","year":"2014","journal-title":"J. Signal Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"337","DOI":"10.3233\/ICA-170551","article-title":"Image recognition with deep neural networks in presence of noise\u2013dealing with and taking advantage of distortions","volume":"24","author":"Koziarski","year":"2017","journal-title":"Integr. Comput.-Aided Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s00138-011-0394-0","article-title":"An innovative methodology for detection and quantification of cracks through incorporation of depth perception","volume":"24","author":"Jahanshahi","year":"2013","journal-title":"Mach. Vis. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.autcon.2016.06.008","article-title":"Vision-based detection of loosened bolts using the Hough transform and support vector machines","volume":"71","author":"Cha","year":"2016","journal-title":"Autom. Constr."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/j.advengsoft.2006.06.002","article-title":"PCA-based algorithm for unsupervised bridge crack detection","volume":"37","author":"Abudayyeh","year":"2006","journal-title":"Adv. Eng. Softw."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e2766","DOI":"10.1002\/stc.2766","article-title":"Surface crack detection based on image stitching and transfer learning with pretrained convolutional neural network","volume":"28","author":"Wu","year":"2021","journal-title":"Struct. Control Health Monit."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Azimi, M., Eslamlou, A.D., and Pekcan, G. (2020). Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors, 20.","DOI":"10.3390\/s20102778"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"8016","DOI":"10.1109\/TIE.2019.2945265","article-title":"SDDNet: Real-time crack segmentation","volume":"67","author":"Choi","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1111\/mice.12549","article-title":"Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks","volume":"35","author":"Pan","year":"2020","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1111\/mice.12313","article-title":"Structural damage detection with automatic feature-extraction through deep learning","volume":"32","author":"Lin","year":"2017","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_19","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., and Jia, Y. (2015, January 10). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, C., Chen, J., Li, Z., and Huang, Y. (2021). Structural crack detection and recognition based on deep learning. Appl. Sci., 11.","DOI":"10.3390\/app11062868"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1111\/mice.12411","article-title":"Damage classification for masonry historic structures using convolutional neural networks based on still images","volume":"33","author":"Wang","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103606","DOI":"10.1016\/j.autcon.2021.103606","article-title":"Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning","volume":"125","author":"Dais","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"105246","DOI":"10.1016\/j.jobe.2022.105246","article-title":"Vision-based concrete crack detection using a hybrid framework considering noise effect","volume":"61","author":"Yu","year":"2022","journal-title":"J. Build. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e3079","DOI":"10.1002\/stc.3079","article-title":"Multiclass damage detection in concrete structures using a transfer learning-based generative adversarial network","volume":"29","author":"Dunphy","year":"2022","journal-title":"Struct. Control. Health Monit."},{"key":"ref_27","first-page":"e2507","article-title":"Deep learning-based multi-class damage detection for autonomous post-disaster reconnaissance","volume":"27","author":"Jahanshahi","year":"2020","journal-title":"Struct. Control Health Monit."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.autcon.2018.06.007","article-title":"Convolutional neural networks: Computer vision-based workforce activity assessment in construction","volume":"94","author":"Luo","year":"2018","journal-title":"Autom. Constr."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/TITS.2020.2990703","article-title":"CrackGAN: Pavement crack detection using partially accurate ground truths based on generative adversarial learning","volume":"22","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_30","unstructured":"\u00c7a\u011flar, F.O., and \u00d6zgenel, R. (2022, August 20). Concrete Crack Images for Classification. Available online: https:\/\/data.mendeley.com\/datasets\/5y9wdsg2zt\/2."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1111\/mice.12622","article-title":"Automated pavement crack detection and segmentation based on two-step convolutional neural network","volume":"35","author":"Liu","year":"2020","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1111\/mice.12412","article-title":"Automatic pixel-level crack detection and measurement using fully convolutional network","volume":"33","author":"Yang","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e2850","DOI":"10.1002\/stc.2850","article-title":"Deep convolutional neural networks for semantic segmentation of cracks","volume":"29","author":"Wang","year":"2022","journal-title":"Struct. Control Health Monit."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"109914","DOI":"10.1016\/j.measurement.2021.109914","article-title":"Pixel-level pavement crack segmentation with encoder-decoder network","volume":"184","author":"Tang","year":"2021","journal-title":"Measurement"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"04020064","DOI":"10.1061\/(ASCE)CP.1943-5487.0000954","article-title":"Bridge inspection with aerial robots: Automating the entire pipeline of visual data capture, 3D mapping, defect detection, analysis, and reporting","volume":"35","author":"Lin","year":"2021","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Dai Wenyuan, Y.Q., Guirong, X., and Yong, Y. (2007, January 20\u201324). Boosting for transfer learning. Proceedings of the 24th International Conference on Machine Learning, Corvallis, OR, USA.","DOI":"10.1145\/1273496.1273521"},{"key":"ref_37","unstructured":"Chollet, F. (2022, November 08). Keras Documentation, Available online: https:\/\/keras.io\/."},{"key":"ref_38","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e2551","DOI":"10.1002\/stc.2551","article-title":"CrackU-net: A novel deep convolutional neural network for pixelwise pavement crack detection","volume":"27","author":"Huyan","year":"2020","journal-title":"Struct. Control Health Monit."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Poojary, R., and Pai, A. (2019, January 19\u201321). Comparative study of model optimization techniques in fine-tuned CNN models. Proceedings of the 2019 International Conference on Electrical and Computing Technologies and Applications (ICECTA), Ras Al Khaimah, United Arab Emirates.","DOI":"10.1109\/ICECTA48151.2019.8959681"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kumar, A., Sarkar, S., and Pradhan, C. (2020). Malaria Disease Detection Using CNN Technique with sgd, rmsprop and adam Optimizers. Deep Learning Techniques for Biomedical and Health Informatics, Springer.","DOI":"10.1007\/978-3-030-33966-1_11"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"012008","DOI":"10.1088\/1742-6596\/1998\/1\/012008","article-title":"Assessment of optimizers impact on image recognition with convolutional neural network to adversarial datasets","volume":"1998","author":"Agarwal","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"11098","DOI":"10.1016\/j.matpr.2021.02.244","article-title":"Comparison of different optimizers implemented on the deep learning architectures for COVID-19 classification","volume":"46","author":"Verma","year":"2021","journal-title":"Mater. Today Proc."},{"key":"ref_44","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume":"48","author":"Hardt","year":"2016","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_45","first-page":"1","article-title":"The marginal value of adaptive gradient methods in machine learning","volume":"30","author":"Wilson","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8714\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:14:36Z","timestamp":1760145276000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,11]]},"references-count":45,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228714"],"URL":"https:\/\/doi.org\/10.3390\/s22228714","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,11]]}}}