{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T15:25:03Z","timestamp":1771169103691,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["222102220035"],"award-info":[{"award-number":["222102220035"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["232102320068"],"award-info":[{"award-number":["232102320068"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Henan Province Science and technology project","award":["222102220035"],"award-info":[{"award-number":["222102220035"]}]},{"name":"China Henan Province Science and technology project","award":["232102320068"],"award-info":[{"award-number":["232102320068"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A high-quality dataset is a basic requirement to ensure the training quality and prediction accuracy of a deep learning network model (DLNM). To explore the influence of label image accuracy on the performance of a concrete crack segmentation network model in a semantic segmentation dataset, this study uses three labelling strategies, namely pixel-level fine labelling, outer contour widening labelling and topological structure widening labelling, respectively, to generate crack label images and construct three sets of crack semantic segmentation datasets with different accuracy. Four semantic segmentation network models (SSNMs), U-Net, High-Resolution Net (HRNet)V2, Pyramid Scene Parsing Network (PSPNet) and DeepLabV3+, were used for learning and training. The results show that the datasets constructed from the crack label images with pix-el-level fine labelling are more conducive to improving the accuracy of the network model for crack image segmentation. The U-Net had the best performance among the four SSNMs. The Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA) and Accuracy reached 85.47%, 90.86% and 98.66%, respectively. The average difference between the quantized width of the crack image segmentation obtained by U-Net and the real crack width was 0.734 pixels, the maximum difference was 1.997 pixels, and the minimum difference was 0.141 pixels. Therefore, to improve the segmentation accuracy of crack images, the pixel-level fine labelling strategy and U-Net are the best choices.<\/jats:p>","DOI":"10.3390\/s24041068","type":"journal-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T12:38:24Z","timestamp":1707223104000},"page":"1068","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Study on the Influence of Label Image Accuracy on the Performance of Concrete Crack Segmentation Network Models"],"prefix":"10.3390","volume":"24","author":[{"given":"Kaifeng","family":"Ma","sequence":"first","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengshu","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlong","family":"Shang","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1220-2876","authenticated-orcid":false,"given":"Jinping","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhen","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peipei","family":"He","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9406-0535","authenticated-orcid":false,"given":"Shiming","family":"Li","sequence":"additional","affiliation":[{"name":"College of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450046, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"ref_1","first-page":"187","article-title":"Surface crack detection of concrete structures based on deep learning","volume":"394","author":"Li","year":"2022","journal-title":"Concrete"},{"key":"ref_2","first-page":"1","article-title":"Method for detecting cracks in concrete strucyures based on deep learning and UAV","volume":"54","author":"Ding","year":"2021","journal-title":"China Civ. Eng. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2718","DOI":"10.1109\/TITS.2015.2477675","article-title":"Automatic crack detection on two-dimensional pavement images: An algorithm based on minimal path selection","volume":"17","author":"Amhaz","year":"2016","journal-title":"IEEE Trans. Intell. Transp."},{"key":"ref_4","first-page":"518","article-title":"Crack detection of 3D asphalt pavement based on multi-feature test","volume":"55","author":"Qiu","year":"2020","journal-title":"J. Southwest Jiaotong Univ."},{"key":"ref_5","first-page":"3143","article-title":"Pavement crack segmentation algorithm based on k-means clustering","volume":"41","author":"Li","year":"2020","journal-title":"Comput. Eng. Design"},{"key":"ref_6","first-page":"2334","article-title":"Lightweight grid bridge crack detection technology based on depth classification","volume":"43","author":"Wei","year":"2022","journal-title":"Comput. Eng. Design"},{"key":"ref_7","first-page":"65","article-title":"Intelligent identification and measurement of bridge cracks based on YOLOv5 and U-Net3+","volume":"50","author":"Yu","year":"2023","journal-title":"J. Hunan. Univ."},{"key":"ref_8","first-page":"1","article-title":"Review of deep learning-based crack detection for civil infrastructures","volume":"36","author":"Deng","year":"2023","journal-title":"China J. Highw. Transp."},{"key":"ref_9","first-page":"1727","article-title":"Research on detection algorithm for bridge cracks based on deep learning","volume":"45","author":"Li","year":"2019","journal-title":"Acta Autom. Sin."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ma, K.F., Meng, X., Hao, M.S., Huang, G.P., Hu, Q.F., and He, P.P. (2023). Research on the efficiency of bridge crack detection by coupling deep learning frameworks with convolutional neural networks. Sensors, 23.","DOI":"10.3390\/s23167272"},{"key":"ref_11","first-page":"204","article-title":"Crack U-Net: Towards high quality pavement crack detection","volume":"49","author":"Zhu","year":"2022","journal-title":"Comput. Sci."},{"key":"ref_12","first-page":"1718","article-title":"Parallel attention based UNet for crack detection","volume":"58","author":"Liu","year":"2021","journal-title":"Comput. Res. Dev."},{"key":"ref_13","first-page":"1","article-title":"Bridge crack image segmentation method based on improved DeepLabv3+ model","volume":"52","author":"Tan","year":"2022","journal-title":"J. Jilin. Univ."},{"key":"ref_14","first-page":"182","article-title":"Improved Deeplabv3+ pavement crack detection based on maximum connection region collaboration","volume":"40","author":"Huang","year":"2023","journal-title":"Comput. Simul."},{"key":"ref_15","first-page":"101","article-title":"Segmentation algorithm of bridge crack image based on modified PSPNet","volume":"58","author":"Li","year":"2021","journal-title":"Laser Optoelectron. Prog."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105225","DOI":"10.1016\/j.engappai.2022.105225","article-title":"Automated bridge surface crack detection and segmentation using computer vision-based deep learning model","volume":"115","author":"Zhang","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104436","DOI":"10.1016\/j.autcon.2022.104436","article-title":"Multi-scale feature fusion network for pixel-level pavement distress detection","volume":"141","author":"Zhong","year":"2022","journal-title":"Automat. Constr."},{"key":"ref_18","first-page":"161649","article-title":"Lightweight bridge crack detection method based on SegNet and Bottleneck depth-separable convolution with residuals","volume":"9","author":"Zheng","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6080","DOI":"10.1364\/AO.423406","article-title":"Automatic crack segmentation using deep high-resolution representation learning","volume":"60","author":"Chen","year":"2021","journal-title":"Appl. Opt."},{"key":"ref_20","first-page":"7552337","article-title":"Automated pixel- level detection of expansion joints on asphalt pavement using a deep-learning-based approach","volume":"2023","author":"He","year":"2023","journal-title":"Struct. Control. Health"},{"key":"ref_21","first-page":"35","article-title":"Method for bridge crack detection based on the U-Net convolutional networks","volume":"46","author":"Zhu","year":"2019","journal-title":"J. Xidian Univ."},{"key":"ref_22","first-page":"51","article-title":"Bridge crack detection algorithm based on CNN and CRF","volume":"42","author":"Wu","year":"2021","journal-title":"Comput. Eng. Des."},{"key":"ref_23","first-page":"2366","article-title":"Bridge crack detection method based on convolution neural network","volume":"42","author":"Liao","year":"2021","journal-title":"Comput. Eng. Des."},{"key":"ref_24","first-page":"316","article-title":"Research on image semantic segmentation algorithm based on deep learning","volume":"37","author":"Xiang","year":"2020","journal-title":"Appl. Res. Comput."},{"key":"ref_25","first-page":"36","article-title":"Research on image semantic segmentation for complex environments","volume":"46","author":"Wang","year":"2019","journal-title":"Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106472","DOI":"10.1016\/j.engappai.2023.106472","article-title":"Active contour model based on local Kulback-Leibler divergence for fast image segmentation","volume":"123","author":"Yang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_28","first-page":"1","article-title":"Survey of research in image semantic segmentation based on deep neural network","volume":"46","author":"Jing","year":"2020","journal-title":"Comput. Eng."},{"key":"ref_29","first-page":"242","article-title":"A review of image semantic segmentation based on deep learning","volume":"20","author":"Lu","year":"2021","journal-title":"Softw. Guide"},{"key":"ref_30","first-page":"47","article-title":"Survey of image semantic segmentation methods based on deep neural network","volume":"15","author":"Xu","year":"2021","journal-title":"J. Front. Comput. Sci. Technol."},{"key":"ref_31","first-page":"12","article-title":"Survey of image semantic segmentation based on deep learning","volume":"55","author":"Kuang","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1177\/1475921720940068","article-title":"A research on an improved Unet-based concrete crack detection algorithm","volume":"20","author":"Zhang","year":"2020","journal-title":"Struct. Health Monit."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhao, H.S., Shi, J.P., Qi, X.J., Wang, X.G., and Jia, J.Y. (2017, January 21\u201326). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref_36","first-page":"143","article-title":"Research on improved lightweight high resolution human keypoint detection","volume":"57","author":"Liu","year":"2021","journal-title":"Comput. Eng. Appl."},{"key":"ref_37","first-page":"357","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","volume":"41","author":"Chen","year":"2014","journal-title":"Comput. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fuly connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref_39","first-page":"262","article-title":"Bridge crack detection based on improved DeeplabV3+ and migration learning","volume":"59","author":"Zhao","year":"2023","journal-title":"Comput. Eng. Appl."},{"key":"ref_40","first-page":"319","article-title":"Dam crack detection based on multi-source transfer learning","volume":"49","author":"Wang","year":"2022","journal-title":"Comput. Sci."},{"key":"ref_41","unstructured":"Jia, D., Wei, D., Socher, R., Li-Jia, L., Kai, L., and Li, F.F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami, FL, USA."},{"key":"ref_42","unstructured":"Eric, B., and Matthew, H. (2021). Concrete Crack Conglomerate Dataset, University Libraries, Virginia Tech. Dataset."},{"key":"ref_43","unstructured":"Eric, B., and Matthew, H. (2021). Labeled Cracks in the Wild (LCW) Dataset, University Libraries, Virginia Tech. Dataset."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"3434","DOI":"10.1109\/TITS.2016.2552248","article-title":"Automatic road crack detection using random structured forests","volume":"17","author":"Shi","year":"2016","journal-title":"IEEE Trans. Intell. Transp."},{"key":"ref_45","doi-asserted-by":"crossref","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":"ref_46","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1590\/s1678-86212021000100498","article-title":"Digital image processing for automatic detection of cracks in buildings coatings","volume":"21","author":"Ruiz","year":"2021","journal-title":"Ambiente Constru\u00eddo"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.patrec.2011.11.004","article-title":"Crack tree: Automatic crack detection from pavement images","volume":"33","author":"Zou","year":"2012","journal-title":"Pattern. Recogn. Lett."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1109\/TIP.2018.2878966","article-title":"DeepCrack: Learning hierarchical convolutional features for crack detection","volume":"28","author":"Zou","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_49","first-page":"103","article-title":"Method for bridge crack detection based on multiresolution network","volume":"58","author":"Li","year":"2021","journal-title":"Laser Optoelectron. Prog."},{"key":"ref_50","first-page":"2722","article-title":"Research on bridge crack detection based on deep learning under complex background","volume":"17","author":"Yang","year":"2020","journal-title":"J. Railw. Sci. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"111260","DOI":"10.1016\/j.measurement.2022.111260","article-title":"A hybrid method for pavement crack width measurement","volume":"197","author":"Ong","year":"2022","journal-title":"Measurement"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"04016056","DOI":"10.1061\/(ASCE)CP.1943-5487.0000627","article-title":"Methodology for accurate AASHTO PP67-10-based cracking quantification using 1-mm 3D pavement images","volume":"31","author":"Qiu","year":"2017","journal-title":"J. Comput. Civil. Eng."},{"key":"ref_53","first-page":"53","article-title":"Weakly supervised semantic segmentation algorithm based on self-supervised image pair","volume":"42","author":"Hou","year":"2022","journal-title":"J. Comput. Appl."},{"key":"ref_54","first-page":"824","article-title":"Saliency background guided network for weakly-supervised semantic segmentation","volume":"34","author":"Bai","year":"2021","journal-title":"Pattern Recognit. Artif. Intell."},{"key":"ref_55","first-page":"188","article-title":"Weakly-supervised semantic segmentation method of remote rensing images based on edge enhancement","volume":"58","author":"Luan","year":"2022","journal-title":"Comput. Eng. Appl."},{"key":"ref_56","first-page":"440","article-title":"Review of image semantic segmentation based on deep learning","volume":"30","author":"Tian","year":"2019","journal-title":"J. Softw."},{"key":"ref_57","first-page":"894","article-title":"A survey of weakly-supervised image semantic segmentation based on image -level labels","volume":"52","author":"Xie","year":"2021","journal-title":"J. Taiyuan Univ."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"107268","DOI":"10.1016\/j.infsof.2023.107268","article-title":"A survey on dataset quality in machine learning","volume":"162","author":"Gong","year":"2013","journal-title":"Inf. Softw. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1068\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:56:05Z","timestamp":1760104565000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,6]]},"references-count":58,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["s24041068"],"URL":"https:\/\/doi.org\/10.3390\/s24041068","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,6]]}}}