{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:33:19Z","timestamp":1763789599223,"version":"3.45.0"},"reference-count":53,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Data augmentation is one of the effective solutions to improve the performance of machine learning models in general and deep learning in particular. Data augmentation techniques bring different effects to each model, but very few studies have considered this issue. This study investigated the effect of five distinct data augmentation strategies on a custom-built Convolutional Neural Network (CNN) and nine pre-trained CNN models for crack detection. All ten models were initially trained on a reference dataset of unaugmented images, followed by separate experiments using the augmented datasets. The results show that the pre-trained models, especially VGG-16, EfficientNet-B7, Xception, DenseNet-201, and EfficientNet-B0, consistently achieved greater than 98% in accuracy across all augmentation techniques. Meanwhile, the custom-built CNN was very sensitive to illumination changes and noise. Image rotation and cropping have minimal negative impact and sometimes improve performance. The findings demonstrate that combining data augmentation with state-of-the-art pre-trained models offers a powerful and efficient alternative to the reliance on large-scale datasets for accurate crack detection using CNNs.<\/jats:p>","DOI":"10.3390\/app152212321","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:02:42Z","timestamp":1763640162000},"page":"12321","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Effect of Data Augmentation on Performance of Custom and Pre-Trained CNN Models for Crack Detection"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2090-706X","authenticated-orcid":false,"given":"Tope Moses","family":"Omoniyi","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, Nigerian Army University Biu, Biu 603108, Nigeria"}]},{"given":"Barnabas","family":"Abel","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Nigerian Army University Biu, Biu 603108, Nigeria"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0294-328X","authenticated-orcid":false,"given":"Oluwaseun","family":"Omoebamije","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, Nigerian Army University Biu, Biu 603108, Nigeria"}]},{"given":"Zuberu Mark","family":"Onimisi","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, Nigerian Army University Biu, Biu 603108, Nigeria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1536-2149","authenticated-orcid":false,"given":"Jose C.","family":"Matos","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6824-5221","authenticated-orcid":false,"given":"Joaquim","family":"Tinoco","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]},{"given":"Tran Quang","family":"Minh","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, ARISE, ISISE, University of Minho, 4800-058 Guimar\u00e3es, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"102297","DOI":"10.1016\/j.asej.2023.102297","article-title":"Application of deep learning in damage classification of reinforced concrete bridges","volume":"15","author":"Abubakr","year":"2024","journal-title":"Ain Shams Eng. J."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1007\/s41062-023-01209-3","article-title":"An improved deep learning convolutional neural network for crack detection based on UAV images","volume":"8","author":"Omoebamije","year":"2023","journal-title":"Innov. Infrastruct. Solut."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1016\/j.conbuildmat.2018.08.011","article-title":"Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete","volume":"186","author":"Dorafshan","year":"2018","journal-title":"Constr. Build. Mater."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"578","DOI":"10.3390\/automation5040033","article-title":"AI-Driven crack detection for remanufacturing cylinder heads using deep learning and Engineering-Informed data augmentation","volume":"5","author":"Mohammadzadeh","year":"2024","journal-title":"Automation"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"120767","DOI":"10.1016\/j.engstruct.2025.120767","article-title":"Enhancing the Structural Health Monitoring (SHM) through data reconstruction: Integrating 1D convolutional neural networks (1DCNN) with bidirectional long short-term memory networks (Bi-LSTM)","volume":"340","author":"Minh","year":"2025","journal-title":"Eng. Struct."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"117810","DOI":"10.1016\/j.measurement.2025.117810","article-title":"Data reconstruction leverages one-dimensional Convolutional Neural Networks (1DCNN) combined with Long Short-Term Memory (LSTM) networks for Structural Health Monitoring (SHM)","volume":"253","author":"Minh","year":"2025","journal-title":"Measurement"},{"key":"ref_7","first-page":"23012","article-title":"A model for estimating the economic costs of computer vision systems that use deep learning","volume":"38","author":"Thompson","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An Overview of Overfitting and its Solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wen, Q., Gao, J., Sun, L., Xu, H., Lv, J., and Song, X. (2021). Time series data augmentation for deep learning: A survey. arXiv.","DOI":"10.24963\/ijcai.2021\/631"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Feng, S.Y., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T., and Hovy, E. (2021). A survey of Data Augmentation Approaches for NLP. arXiv.","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"ref_13","first-page":"3586","article-title":"Audio augmentation for speech recognition","volume":"2015","author":"Ko","year":"2015","journal-title":"Proc. Interspeech"},{"key":"ref_14","first-page":"1","article-title":"Improve Image Classification Using Data Augmentation and Neural Network","volume":"2","author":"Gu","year":"2019","journal-title":"SMU Data Sci. Rev."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kim, B., and Cho, S. (2018). Automated Vision-Based detection of cracks on concrete surfaces using a deep learning technique. Sensors, 18.","DOI":"10.3390\/s18103452"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"109347","DOI":"10.1016\/j.patcog.2023.109347","article-title":"A comprehensive survey of image augmentation techniques for deep learning","volume":"137","author":"Xu","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_17","first-page":"227","article-title":"Pavement Crack Classification using Deep Convolutional Neural Network","volume":"1","author":"Osman","year":"2021","journal-title":"J. Mech. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nguyen, C.L., Nguyen, A., Brown, J., Byrne, T., Ngo, B.T., and Luong, C.X. (2024). Optimising Concrete Crack Detection: A Study of Transfer Learning with Application on Nvidia Jetson Nano. Sensors, 24.","DOI":"10.3390\/s24237818"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhu, Y., Yang, M., Jin, G., Zhu, Y., Lu, Y., Zou, Y., and Chen, Q. (2024). An improved sample selection framework for learning with noisy labels. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0309841"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"111284","DOI":"10.1016\/j.patcog.2024.111284","article-title":"A progressive sample selection framework with contrastive loss designed for noisy labels","volume":"16","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kim, J., Seon, S., Kim, S., Sun, Y., Lee, S., Kim, J., Hwang, B., and Kim, J. (2024). Generative AI-Driven Data Augmentation for Crack Detection in Physical Structures. Electronics, 13.","DOI":"10.3390\/electronics13193905"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.undsp.2022.07.003","article-title":"Automatic tunnel lining crack detection via deep learning with generative adversarial network-based data augmentation","volume":"9","author":"Zhou","year":"2022","journal-title":"Undergr. Space"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Choi, S.M., Cha, H.S., and Jiang, S. (2024). Hybrid Data Augmentation for Enhanced Crack Detection in Building Construction. Buildings, 14.","DOI":"10.3390\/buildings14071929"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Jamshidi, M., El-Badry, M., and Nourian, N. (2023). Improving Concrete Crack Segmentation Networks through CutMix Data Synthesis and Temporal Data Fusion. Sensors, 23.","DOI":"10.3390\/s23010504"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.procs.2024.03.042","article-title":"Machine Learning-Based intrusion detection on multi-class imbalanced dataset using SMOTE","volume":"234","author":"Widodo","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mohammed, R., Rawashdeh, J., and Abdullah, M. (2020, January 7\u20139). Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. Proceedings of the 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.","DOI":"10.1109\/ICICS49469.2020.239556"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Walawalkar, D., Shen, Z., Liu, Z., and Savvides, M. (2020, January 4\u20138). Attentive CutMix: An enhanced data augmentation approach for deep learning based image classification. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR, 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-V4, Inception-ResNet and the impact of residual connections on learning. Proc. AAAI Conf. Artif. Intell., 31.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_31","unstructured":"Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","article-title":"Convolutional Networks with Dense Connectivity","volume":"44","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 17). Identity mappings in deep residual networks. Lecture notes in computer science. Proceedings of the European Conference on Computer Vision, Honolulu, HI, USA.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mittal, K., Gill, K.S., Chattopadhyay, S., and Singh, M. (2024, January 17\u201318). Innovative Solutions for solar panel maintenance: A VGG16-Based approach for early damage Detection. Proceedings of the International Conference on Communication, Computing and Internet of Things (IC3IoT), Chennai, India.","DOI":"10.1109\/IC3IoT60841.2024.10550368"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e38104","DOI":"10.1016\/j.heliyon.2024.e38104","article-title":"Deep neural networks for automated damage classification in image-based visual data of reinforced concrete structures","volume":"10","author":"Fan","year":"2024","journal-title":"Heliyon"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e30957","DOI":"10.1016\/j.heliyon.2024.e30957","article-title":"Automatic detection of potholes using VGG-16 pre-trained network and Convolutional Neural Network","volume":"10","author":"Swain","year":"2024","journal-title":"Heliyon"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"105098","DOI":"10.1016\/j.autcon.2023.105098","article-title":"Extended efficient convolutional neural network for concrete crack detection with illustrated merits","volume":"156","author":"Fu","year":"2023","journal-title":"Autom. Constr."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ali, H., Shifa, N., Benlamri, R., Farooque, A.A., and Yaqub, R. (2025). A fine-tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-04479-2"},{"key":"ref_41","first-page":"617","article-title":"A novel deep neural network model based Xception and genetic algorithm for detection of COVID-19 from X-ray images","volume":"328","year":"2022","journal-title":"Ann. Oper. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Joshi, S.A., Bongale, A.M., Olsson, P.O., Urolagin, S., Dharrao, D., and Bongale, A. (2023). Enhanced Pre-Trained Xception Model Transfer learned for breast cancer detection. Computation, 11.","DOI":"10.3390\/computation11030059"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e21097","DOI":"10.1016\/j.heliyon.2023.e21097","article-title":"Mobile-DenseNet: Detection of building concrete surface cracks using a new fusion technique based on deep learning","volume":"9","year":"2023","journal-title":"Heliyon"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Alfaz, N., Hasnat, A., Khan, A., Sayom, N., and Bhowmik, A. (2022, January 11). Bridge Crack Detection Using Dense Convolutional Network (Densenet). Proceedings of the 2nd International Conference on Computing Advancements, New York, NY, USA.","DOI":"10.1145\/3542954.3543027"},{"key":"ref_45","first-page":"11","article-title":"An inception V3 approach for malware classification using machine learning and transfer learning","volume":"4","author":"Ahmed","year":"2023","journal-title":"Int. J. Intell. Netw."},{"key":"ref_46","first-page":"e02530","article-title":"Classification of defects in wooden structures using pre-trained models of convolutional neural network","volume":"19","author":"Ehtisham","year":"2023","journal-title":"Case Stud. Constr. Mater."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Meftah, I., Hu, J., Asham, M.A., Meftah, A., Zhen, L., and Wu, R. (2024). Visual Detection of Road Cracks for Autonomous Vehicles Based on Deep Learning. Sensors, 24.","DOI":"10.3390\/s24051647"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Bao, T. (2023). An Improved ResNet-Based Algorithm for Crack Detection of Concrete Dams Using Dynamic Knowledge Distillation. Water, 15.","DOI":"10.3390\/w15152839"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wen, L., Xiao, Z., Xu, X., and Liu, B. (2025). Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network. Appl. Sci., 15.","DOI":"10.3390\/app15095143"},{"key":"ref_50","unstructured":"Zhou, J.H. (2025, November 10). Noise Crack Dataset. GitHub. Available online: https:\/\/github.com\/zhoujh2020\/."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Zhang, R., Jiang, H., Wang, W., and Liu, J. (2025). Optimization Methods, Challenges, and Opportunities for Edge Inference: A Comprehensive Survey. Electronics, 14.","DOI":"10.3390\/electronics14071345"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Alomar, K., Aysel, H.I., and Cai, X. (2023). Data Augmentation in Classification and Segmentation: A Survey and New Strategies. J. Imaging, 9.","DOI":"10.3390\/jimaging9020046"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"\u0160egota, B.M., Lorencin, I., and An\u0111eli\u0107, N. (2025). Data Augmentation-Driven Improvements in Malignant Lymphoma Image Classification. Computers, 14.","DOI":"10.3390\/computers14070252"}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/22\/12321\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:28:47Z","timestamp":1763789327000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/22\/12321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":53,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["app152212321"],"URL":"https:\/\/doi.org\/10.3390\/app152212321","relation":{},"ISSN":["2076-3417"],"issn-type":[{"type":"electronic","value":"2076-3417"}],"subject":[],"published":{"date-parts":[[2025,11,20]]}}}