{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T08:47:10Z","timestamp":1783500430953,"version":"3.55.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This paper presents a crack detection framework employing a hybrid model that integrates the Swin Transformer with an Enhanced Features Representation Block (EFRB) to precisely detect cracks in images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The Swin Transformer captures long-range dependencies and efficiently processes complex images, forming the backbone of the feature extraction process. The EFRB improved spatial granularity through depthwise convolutions, that focus on spatial features independently across each channel, and pointwise convolutions to improve channel representation. The proposed model used residual connections to enable deeper networks to overcome vanishing gradient problem.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and discussion<\/jats:title>\n                    <jats:p>The training process is optimized using population-based feature selection, resulting in robust performance. The network is trained on a dataset split into 80% training and 20% testing, with a learning rate of 1e-3, batch size of 16, and 30 epochs. Evaluation results show that the model achieves an accuracy of 98%, with precision, recall, and F1-scores as 0.97, 0.99, and 0.98 for crack detection, respectively. These results show the effectiveness of the proposed architecture for real-world crack detection applications in structural monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1655091","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T07:44:01Z","timestamp":1764661441000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Crack detection in structural images using a hybrid Swin Transformer and enhanced features representation block"],"prefix":"10.3389","volume":"8","author":[{"given":"N.","family":"Anusha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L. Jani","family":"Anbarasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"3536","DOI":"10.1080\/10298436.2021.1905808","article-title":"An integrated machine learning model for automatic road crack detection and classification in urban areas","volume":"23","author":"Ahmadi","year":"2022","journal-title":"Int. J. Pavement Eng."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.3390\/buildings13071814","article-title":"Building surface crack detection using deep learning technology","volume":"13","author":"Chen","year":"2023","journal-title":"Buildings"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"5252","DOI":"10.3390\/s24165252","article-title":"Concrete surface crack detection algorithm based on improved YOLOv8","volume":"24","author":"Dong","year":"2024","journal-title":"Sensors"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"3276","DOI":"10.3390\/s25113276","article-title":"Study on lightweight bridge crack detection algorithm based on YOLO11","volume":"25","author":"Dong","year":"2025","journal-title":"Sensors"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1108\/JEDT-04-2021-0192","article-title":"Developing a new deep learning CNN model to detect and classify highway cracks","volume":"20","author":"Elghaish","year":"2022","journal-title":"J. Eng. Des. Technol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2960","DOI":"10.3390\/ma13132960","article-title":"Automatic crack detection on road pavements using encoder-decoder architecture","volume":"13","author":"Fan","year":"2020","journal-title":"Materials"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/s44147-024-00391-0","article-title":"Research on road surface crack detection based on SegNet network","volume":"71","author":"Guo","year":"2024","journal-title":"J. Eng. Appl. Sci."},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v33i01.33018368","article-title":"Depthwise convolution is all you need for learning multiple visual domains","author":"Guo","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"108312","DOI":"10.1016\/j.engappai.2024.108312","article-title":"A two-stage framework for pixel-level pavement surface crack detection","volume":"133","author":"Guo","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"114443","DOI":"10.1016\/j.measurement.2024.114443","article-title":"Road surface crack detection method based on improved YOLOv5 and vehicle-mounted images","volume":"229","author":"Hu","year":"2024","journal-title":"Measurement"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00109","article-title":"Pointwise convolutional neural networks","author":"Hua","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1080\/15583058.2024.2376177","article-title":"Automated surface crack detection in historical constructions with various materials using deep learning-based YOLO network","volume":"19","author":"Karimi","year":"2024","journal-title":"Int. J. Architect. Herit."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.3390\/s23136070","article-title":"Image-processing-based subway tunnel crack detection system","volume":"23","author":"Liu","year":"2023","journal-title":"Sensors"},{"key":"ref14","first-page":"10012","article-title":"Swin Transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"104383","DOI":"10.1016\/j.autcon.2022.104383","article-title":"Deep learning and infrared thermography for asphalt pavement crack severity classification","volume":"140","author":"Liu","year":"","journal-title":"Autom. Constr."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"104575","DOI":"10.1016\/j.autcon.2022.104575","article-title":"Asphalt pavement fatigue crack severity classification by infrared thermography and deep learning","volume":"143","author":"Liu","year":"","journal-title":"Autom. Constr."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"105355","DOI":"10.1016\/j.autcon.2024.105355","article-title":"Multiple-type distress detection in asphalt concrete pavement using infrared thermography and deep learning","volume":"161","author":"Liu","year":"2024","journal-title":"Autom. Constr."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s43251-023-00106-0","article-title":"Weakly-supervised structural surface crack detection algorithm based on class activation map and superpixel segmentation","volume":"4","author":"Liu","year":"2023","journal-title":"Adv. Bridge Eng."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.neucom.2019.01.036","article-title":"Deepcrack: a deep hierarchical feature learning architecture for crack segmentation","volume":"338","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"103858","DOI":"10.1016\/j.earscirev.2021.103858","article-title":"Deep learning for geological hazards analysis: data, models, applications, and opportunities","volume":"223","author":"Ma","year":"2021","journal-title":"Earth-Sci. Rev."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1111\/mice.12932","article-title":"Methodology to integrate augmented reality and pattern recognition for crack detection","volume":"38","author":"Malek","year":"2023","journal-title":"Comput. Aided Civ. Inf. Eng."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.12.022","article-title":"SCA: a sine cosine algorithm for solving optimization problems","volume":"96","author":"Mirjalili","year":"2016","journal-title":"Knowl. Based Syst."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"115718","DOI":"10.1016\/j.eswa.2021.115718","article-title":"Two-stage convolutional neural network for road crack detection and segmentation","volume":"186","author":"Nguyen","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"4981","DOI":"10.3390\/app13084981","article-title":"Concrete crack width measurement using a laser beam and image processing algorithms","volume":"13","author":"Nyathi","year":"2023","journal-title":"Appl. Sci."},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/ICIP.2014.7025160","article-title":"CrackIT\u2014an image processing toolbox for crack detection and characterization","volume-title":"2014 IEEE international conference on image processing (ICIP)","author":"Oliveira","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"126","DOI":"10.3141\/1889-14","article-title":"Infrared thermography for asphalt crack imaging and automated detection","volume":"1889","author":"Oloufa","year":"2004","journal-title":"Transp. Res. Rec."},{"key":"ref27","volume-title":"Concrete crack images for classification","author":"\u00d6zgenel","year":"2019"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.22260\/ISARC2018\/0094","volume-title":"Performance comparison of pretrained convolutional neural networks on crack detection in buildings","author":"\u00d6zgenel","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"112832","DOI":"10.1016\/j.measurement.2023.112832","article-title":"Automatic detection and measurement of ground crack propagation using deep learning networks and an image processing technique","volume":"215","author":"Pham","year":"2023","journal-title":"Measurement"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"108821","DOI":"10.1016\/j.compbiomed.2024.108821","article-title":"Cotconet: an optimized coupled transformer-convolutional network with an adaptive graph reconstruction for leukemia detection","volume":"179","author":"Raghaw","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.11517","article-title":"A real-time concrete crack detection and segmentation model based on YOLOv11","author":"Shaoze","year":"2025","journal-title":"arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.10902","article-title":"Enhancing road crack detection accuracy with BsS-YOLO: optimizing feature fusion and attention mechanisms","author":"Tang","year":"2024","journal-title":"arXiv"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"132839","DOI":"10.1016\/j.conbuildmat.2023.132839","article-title":"Advanced crack detection and segmentation on bridge decks using deep learning","volume":"400","author":"Tran","year":"2023","journal-title":"Constr. Build. Mater."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1016\/j.matpr.2022.11.356","article-title":"Concrete bridge crack detection by image processing technique by using the improved OTSU method","volume":"74","author":"Vivekananthan","year":"2023","journal-title":"Mater Today Proc"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"107085","DOI":"10.1016\/j.engappai.2023.107085","article-title":"Deep learning algorithm for real-time automatic crack detection, segmentation, qualification","volume":"126","author":"Xu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1007\/s00138-009-0189-8","article-title":"Fast crack detection method for large-size concrete surface images using percolation-based image processing","volume":"21","author":"Yamaguchi","year":"2010","journal-title":"Mach. Vis. Appl."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"110684","DOI":"10.1016\/j.knosys.2023.110684","article-title":"CoWNet: a correlation weighted network for geological hazard detection","volume":"275","author":"Yin","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"101335","DOI":"10.1016\/j.trgeo.2024.101335","article-title":"Real-time pavement surface crack detection based on lightweight semantic segmentation model","volume":"48","author":"Yu","year":"2024","journal-title":"Transp. Geotech."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10061654","article-title":"Concrete surface crack detection with convolutional-based deep learning models","author":"Zadeh","year":"2024","journal-title":"arXiv"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"131941","DOI":"10.1016\/j.conbuildmat.2023.131941","article-title":"Mobilenetv3-BLS: a broad learning approach for automatic concrete surface crack detection","volume":"392","author":"Zhang","year":"","journal-title":"Constr. Build. Mater."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1007\/s40747-022-00876-6","article-title":"Automated bridge crack detection method based on lightweight vision models","volume":"9","author":"Zhang","year":"","journal-title":"Complex Intell. Syst."},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/ICIP.2016.7533052","article-title":"Road crack detection using deep convolutional neural network","author":"Zhang","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"9120","DOI":"10.3390\/app15169120","article-title":"Review of crack depth detection technology for engineering structures: from physical principles to artificial intelligence","volume":"15","author":"Zhao","year":"2025","journal-title":"Appl. Sci."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s43251-022-00070-1","article-title":"State-of-the-art and annual progress of bridge engineering in 2021","volume":"3","author":"Zhao","year":"2022","journal-title":"Adv. Bridge Eng."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"3427","DOI":"10.3390\/s25113427","article-title":"FD2-YOLO: a frequency-domain dual-stream network based on YOLO for crack detection","volume":"25","author":"Zhu","year":"2025","journal-title":"Sensors"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1655091\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T07:44:03Z","timestamp":1764661443000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1655091\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":45,"alternative-id":["10.3389\/frai.2025.1655091"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1655091","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"article-number":"1655091"}}