Crack Detection in Churches using Deep Learning

Crack Detection in Churches using Deep Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Crack Detection in Churches using Deep Learning Matteo Bozzano, Mohamedel Mustafa Omeribrahim Eid, Serena Cattari, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8995413/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Post-earthquake damage assessment of churches is a critical task, due to the architectural complexity and the safety risks associated with on-site inspections, which expose surveyors to potentially dangerous structurally compromised areas. Among visible indicators, cracks represent one of the most relevant features for evaluating structural damage. As part of the wider project RAISE (NRRP-ECS00000035), this study proposes an image-based deep learning approach for automatic crack detection in church buildings, with the aim of supporting traditional survey procedures and reducing both inspection time and operator risk. A convolutional neural network based on transfer learning is developed and evaluated using the Xception architecture. The model is first trained on a large benchmark dataset already available of concrete crack images. Image patches are extracted and classified in a binary framework (crack vs. non-crack), and model performance is assessed using standard metrics such as Precision, Recall, and F1-score. While initial training on concrete images yields satisfactory results (98% accuracy), performance drops significantly when applied to church images, highlighting a strong domain shift. Retraining with church-specific data, a custom dataset collected from churches in the Liguria region, including surfaces characterized by frescoes, plaster, and decorative elements, substantially improves performance. It achieves a Precision of 93.87%, a Recall of 88.45%, and an F1-score of 91.08% on frescoed surfaces of the vaults, a fundamental element in the damage survey phase. Additional tests investigate the influence of lighting conditions, image resolution, and capture distance, providing practical guidance for acquisition protocol design. The results demonstrate the potential of deep learning techniques for supporting crack detection in heritage contexts, while also highlighting current limitations related to data variability and patch-level classification. Future developments will focus on dataset expansion, pixel-level segmentation approaches, and integration with standardized damage assessment frameworks. image immovable artistic assets damage binary classification convolutional neural network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 Apr, 2026 Reviews received at journal 30 Mar, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers invited by journal 15 Mar, 2026 Editor assigned by journal 10 Mar, 2026 Submission checks completed at journal 05 Mar, 2026 First submitted to journal 28 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8995413","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":607062361,"identity":"9f7abd6c-57ee-4913-b18a-8dff4ce5b491","order_by":0,"name":"Matteo Bozzano","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIiWNgGAWjYBCDBChtw8BwAEQbADEzLsXMjA1IWtKQteDSg6rlMFQLRAqrBt3288cffKhgyOPnP/7wc0HFeTm+Gwls0gUFtXIM7PwHsGkxO5PM2DjjDEOxZMOBZOkZZ24bS4K0zDA4bozLYWYHkhmbedsYEjccbDggzdt2O3EDSAuPwbHEBlxazj9mbP4L0nKYsfk3b9u5epiWepxabgBtYQRpOcbMBrTlQIIBREtNAk6H3XhsOLPnjESxZA8bmzXPmWTDmWceNlvzGBwwbGNmNsDusMQHH35U2IBC7PFtngo7eb7jyQdv8/ypk+fnP/gAqzUQIIHMAUfUYQY2POqxgjpSNYyCUTAKRsHwBQAlPVzxEFbwFQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Genova","correspondingAuthor":true,"prefix":"","firstName":"Matteo","middleName":"","lastName":"Bozzano","suffix":""},{"id":607062362,"identity":"f67f3633-1cb8-488d-9e80-e61bf525f602","order_by":1,"name":"Mohamedel Mustafa Omeribrahim Eid","email":"","orcid":"","institution":"Bruno Kessler Foundation","correspondingAuthor":false,"prefix":"","firstName":"Mohamedel","middleName":"Mustafa Omeribrahim","lastName":"Eid","suffix":""},{"id":607062363,"identity":"2c5157b1-cd27-45e9-85d9-229fcdd8dc48","order_by":2,"name":"Serena Cattari","email":"","orcid":"","institution":"University of Genova","correspondingAuthor":false,"prefix":"","firstName":"Serena","middleName":"","lastName":"Cattari","suffix":""},{"id":607062364,"identity":"4c778cc2-e58f-4426-bece-d3404c0f1e32","order_by":3,"name":"Bianca Federici","email":"","orcid":"","institution":"University of Genova","correspondingAuthor":false,"prefix":"","firstName":"Bianca","middleName":"","lastName":"Federici","suffix":""}],"badges":[],"createdAt":"2026-02-28 12:53:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8995413/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8995413/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105033639,"identity":"215d5912-8e37-40f3-b326-94be084da3de","added_by":"auto","created_at":"2026-03-20 07:21:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2735040,"visible":true,"origin":"","legend":"","description":"","filename":"CrackDetectioninChurchesusingDeepLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8995413/v1_covered_f7dfcc9a-b65b-4529-a031-0f58bb647520.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Crack Detection in Churches using Deep Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"applied-geomatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agmj","sideBox":"Learn more about [Applied Geomatics](http://link.springer.com/journal/12518)","snPcode":"12518","submissionUrl":"https://submission.nature.com/new-submission/12518/3","title":"Applied Geomatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"image, immovable artistic assets, damage, binary classification, convolutional neural network","lastPublishedDoi":"10.21203/rs.3.rs-8995413/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8995413/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Post-earthquake damage assessment of churches is a critical task, due to the architectural complexity and the safety risks associated with on-site inspections, which expose surveyors to potentially dangerous structurally compromised areas. Among visible indicators, cracks represent one of the most relevant features for evaluating structural damage. As part of the wider project RAISE (NRRP-ECS00000035), this study proposes an image-based deep learning approach for automatic crack detection in church buildings, with the aim of supporting traditional survey procedures and reducing both inspection time and operator risk. A convolutional neural network based on transfer learning is developed and evaluated using the Xception architecture. The model is first trained on a large benchmark dataset already available of concrete crack images. Image patches are extracted and classified in a binary framework (crack vs. non-crack), and model performance is assessed using standard metrics such as Precision, Recall, and F1-score. While initial training on concrete images yields satisfactory results (98\\% accuracy), performance drops significantly when applied to church images, highlighting a strong domain shift. Retraining with church-specific data, a custom dataset collected from churches in the Liguria region, including surfaces characterized by frescoes, plaster, and decorative elements, substantially improves performance. It achieves a Precision of 93.87\\%, a Recall of 88.45\\%, and an F1-score of 91.08\\% on frescoed surfaces of the vaults, a fundamental element in the damage survey phase. Additional tests investigate the influence of lighting conditions, image resolution, and capture distance, providing practical guidance for acquisition protocol design. The results demonstrate the potential of deep learning techniques for supporting crack detection in heritage contexts, while also highlighting current limitations related to data variability and patch-level classification. Future developments will focus on dataset expansion, pixel-level segmentation approaches, and integration with standardized damage assessment frameworks.","manuscriptTitle":"Crack Detection in Churches using Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-17 22:35:13","doi":"10.21203/rs.3.rs-8995413/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-04T18:21:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-30T16:51:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"211864712648411246060619181922762433181","date":"2026-03-16T16:06:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-15T19:23:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-10T13:01:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-05T05:54:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Applied Geomatics","date":"2026-02-28T12:38:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"applied-geomatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agmj","sideBox":"Learn more about [Applied Geomatics](http://link.springer.com/journal/12518)","snPcode":"12518","submissionUrl":"https://submission.nature.com/new-submission/12518/3","title":"Applied Geomatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"c567bd19-86c7-4655-8f6f-50cc2001b142","owner":[],"postedDate":"March 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-14T11:54:53+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-17 22:35:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8995413","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8995413","identity":"rs-8995413","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}