Building Shape Recognition Based on Improved ZFNet for Map Generalization

Building Shape Recognition Based on Improved ZFNet for Map Generalization | 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 Building Shape Recognition Based on Improved ZFNet for Map Generalization Huimin Liu, Chengkai Tan, Jianbo Tang, Min Deng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7548575/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Feb, 2026 Read the published version in Journal of Geovisualization and Spatial Analysis → Version 1 posted You are reading this latest preprint version Abstract Maintaining building shape across different levels of map generalization is essential for preserving spatial accuracy and readability. Targeted and differentiated map generalization algorithms can achieve higher shape-maintaining performance, and these algorithms need the strong support of accurate building shape recognition. Traditional building shape classification methods based on template matching often suffer from high complexity, low accuracy, and poor generalization capability. Meanwhile, existing convolutional neural network (CNN)-based approaches lack optimized network structures tailored to building features, resulting in limited classification performance. To address these challenges, this study proposes an improved ZFNet-based classification method specifically designed for single-channel building images, which typically exhibit regular geometries and simple feature representations. To reduce complexity and avoid overfitting, the model simplifies the original ZFNet by removing its fifth convolutional layer. Batch normalization layers are added after each convolutional layer, kernel sizes are refined, and the activation function is adjusted for improved performance. Experimental results demonstrate that the improved ZFNet achieves a test accuracy of 98.53%, outperforming AlexNet by approximately 5.5%. Furthermore, it exhibits superior F1-Scores across most shape categories, except for cross-shaped buildings, while maintaining a more lightweight architecture with lower computational cost. Compared with two variants of Graph Convolutional Neural Networks (GCN), the proposed method also shows better model performance, providing a robust foundation for addressing key challenges in building synthesis, such as feature preservation. Deep Learning Map generalization Convolutional Neural Network Building shape recognition Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Feb, 2026 Read the published version in Journal of Geovisualization and Spatial Analysis → Version 1 posted 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-7548575","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":516413475,"identity":"057502e4-fbe5-46cf-bc16-ebd61c9110af","order_by":0,"name":"Huimin Liu","email":"","orcid":"","institution":"Central South University","correspondingAuthor":false,"prefix":"","firstName":"Huimin","middleName":"","lastName":"Liu","suffix":""},{"id":516413476,"identity":"7e849039-730e-4a25-baa7-833cbed38b60","order_by":1,"name":"Chengkai Tan","email":"","orcid":"","institution":"Central South University","correspondingAuthor":false,"prefix":"","firstName":"Chengkai","middleName":"","lastName":"Tan","suffix":""},{"id":516413477,"identity":"de6721c8-ecc3-4f85-b5d3-6be0063960b3","order_by":2,"name":"Jianbo Tang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYBACxmYGBmYY+wGETiBOiwQQMxsQpQUEYFrYJIjSwtzO/OxxQQVDHf/s9msVP/4cZuBnzzFg+LkDn8PYzI1nnGGQkLhzpuxmb9thBsmeNwaMvWfw+sVMmrcN6LAbOWm3GRsOMxjcyDFgZmzDp4X9G1iLPFBLMQPQYfaEtfBAbDG4kX6MmYENaIsEYS1l0jPOSEhuvJHDLNnbls4jceZZwcFePFoM+49vky6osOGXu5H+8MOPP9Zy/O3JGx/8xKelAUyBYoQHHJM8IOIAbg0MDPIIJvsDfApHwSgYBaNgBAMAsANJi7YhZd0AAAAASUVORK5CYII=","orcid":"","institution":"Central South University","correspondingAuthor":true,"prefix":"","firstName":"Jianbo","middleName":"","lastName":"Tang","suffix":""},{"id":516413478,"identity":"31b72c7b-7770-4713-b701-a33ee913f445","order_by":3,"name":"Min Deng","email":"","orcid":"","institution":"Central South University","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Deng","suffix":""}],"badges":[],"createdAt":"2025-09-06 05:53:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7548575/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7548575/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41651-026-00249-4","type":"published","date":"2026-02-25T15:59:25+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":103765709,"identity":"75d0bb72-7dca-4d22-8bbd-d72ed4c0e6be","added_by":"auto","created_at":"2026-03-02 16:07:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1506531,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript1noauthors.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7548575/v1_covered_4725cf3e-e687-4ffb-b056-d041ef9ae558.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Building Shape Recognition Based on Improved ZFNet for Map Generalization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Deep Learning, Map generalization, Convolutional Neural Network, Building shape recognition","lastPublishedDoi":"10.21203/rs.3.rs-7548575/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7548575/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMaintaining building shape across different levels of map generalization is essential for preserving spatial accuracy and readability. Targeted and differentiated map generalization algorithms can achieve higher shape-maintaining performance, and these algorithms need the strong support of accurate building shape recognition. Traditional building shape classification methods based on template matching often suffer from high complexity, low accuracy, and poor generalization capability. Meanwhile, existing convolutional neural network (CNN)-based approaches lack optimized network structures tailored to building features, resulting in limited classification performance. To address these challenges, this study proposes an improved ZFNet-based classification method specifically designed for single-channel building images, which typically exhibit regular geometries and simple feature representations. To reduce complexity and avoid overfitting, the model simplifies the original ZFNet by removing its fifth convolutional layer. Batch normalization layers are added after each convolutional layer, kernel sizes are refined, and the activation function is adjusted for improved performance. Experimental results demonstrate that the improved ZFNet achieves a test accuracy of 98.53%, outperforming AlexNet by approximately 5.5%. Furthermore, it exhibits superior F1-Scores across most shape categories, except for cross-shaped buildings, while maintaining a more lightweight architecture with lower computational cost. Compared with two variants of Graph Convolutional Neural Networks (GCN), the proposed method also shows better model performance, providing a robust foundation for addressing key challenges in building synthesis, such as feature preservation.\u003c/p\u003e","manuscriptTitle":"Building Shape Recognition Based on Improved ZFNet for Map Generalization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-14 02:28:55","doi":"10.21203/rs.3.rs-7548575/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6ac37581-ec10-4dac-bcb8-c6e1fe8e9fb7","owner":[],"postedDate":"October 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-02T16:04:45+00:00","versionOfRecord":{"articleIdentity":"rs-7548575","link":"https://doi.org/10.1007/s41651-026-00249-4","journal":{"identity":"journal-of-geovisualization-and-spatial-analysis","isVorOnly":false,"title":"Journal of Geovisualization and Spatial Analysis"},"publishedOn":"2026-02-25 15:59:25","publishedOnDateReadable":"February 25th, 2026"},"versionCreatedAt":"2025-10-14 02:28:55","video":"","vorDoi":"10.1007/s41651-026-00249-4","vorDoiUrl":"https://doi.org/10.1007/s41651-026-00249-4","workflowStages":[]},"version":"v1","identity":"rs-7548575","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7548575","identity":"rs-7548575","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}