Character Recognition for Greek Squeezes | 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 Character Recognition for Greek Squeezes Nicholas R. Howe, Feiran Chang, Isabella Falbo, Tajhini Brown, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5418128/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Jun, 2025 Read the published version in International Journal on Document Analysis and Recognition (IJDAR) → Version 1 posted 14 You are reading this latest preprint version Abstract Squeezes are three-dimensional paper impressions made of stone inscriptions, which have to date received relatively less study than many other forms of historical documents. This paper reports on experiments in text recognition, working with a collection of approximately 30,000 squeezes originally collected from museums and archaeological sites in classical Greece. It explores a number of complementary strategies for character recognition in this medium, with the aim of establishing a strong benchmark in performance. Of the methods studied here, the best achieves a character error rate of 14%. character recognition squeeze Greek inscription Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Jun, 2025 Read the published version in International Journal on Document Analysis and Recognition (IJDAR) → Version 1 posted Editorial decision: Revision requested 10 Feb, 2025 Reviews received at journal 21 Jan, 2025 Reviews received at journal 19 Jan, 2025 Reviews received at journal 10 Jan, 2025 Reviews received at journal 07 Jan, 2025 Reviewers agreed at journal 23 Dec, 2024 Reviewers agreed at journal 23 Dec, 2024 Reviewers agreed at journal 22 Dec, 2024 Reviewers agreed at journal 22 Dec, 2024 Reviewers agreed at journal 11 Dec, 2024 Reviewers invited by journal 10 Dec, 2024 Editor assigned by journal 09 Nov, 2024 Submission checks completed at journal 09 Nov, 2024 First submitted to journal 08 Nov, 2024 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-5418128","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":376162039,"identity":"4cba9604-88d3-4784-b6af-a81dd128cb33","order_by":0,"name":"Nicholas R. Howe","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAApUlEQVRIiWNgGAWjYDACCRBRwcDAxsDDACKJ1XIGqJiNJC2MbSDVxGoxl24+JvFxXl00n3zvAYYPZYcJa7GccyxNcua2w7ltbHwJjDPOEaHF4EaO2W3ebQeAWngMmHnbiNXyd04dRMtforUwNjBDtDASpyUt/WfPMZBfcgwO9pxLJ0ZL8mGDHzV1ufObzxg++FFmTVgLCjhAovpRMApGwSgYBbgAALc8OTdhlZ0WAAAAAElFTkSuQmCC","orcid":"","institution":"Smith College","correspondingAuthor":true,"prefix":"","firstName":"Nicholas","middleName":"R.","lastName":"Howe","suffix":""},{"id":376162041,"identity":"27661d07-c9a7-4c79-acc1-7cd52bc9dae2","order_by":1,"name":"Feiran Chang","email":"","orcid":"","institution":"Smith College","correspondingAuthor":false,"prefix":"","firstName":"Feiran","middleName":"","lastName":"Chang","suffix":""},{"id":376162046,"identity":"44f8988c-bdb5-4865-88c7-540a63383acb","order_by":2,"name":"Isabella Falbo","email":"","orcid":"","institution":"Smith College","correspondingAuthor":false,"prefix":"","firstName":"Isabella","middleName":"","lastName":"Falbo","suffix":""},{"id":376162051,"identity":"4e196f0b-a444-4eb5-845c-b290ee64ef58","order_by":3,"name":"Tajhini Brown","email":"","orcid":"","institution":"Smith College","correspondingAuthor":false,"prefix":"","firstName":"Tajhini","middleName":"","lastName":"Brown","suffix":""},{"id":376162052,"identity":"ebe3a843-0063-4119-a290-7ba1261a5457","order_by":4,"name":"Aaron Hershkowitz","email":"","orcid":"","institution":"Institute for Advanced Study","correspondingAuthor":false,"prefix":"","firstName":"Aaron","middleName":"","lastName":"Hershkowitz","suffix":""}],"badges":[],"createdAt":"2024-11-08 17:23:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5418128/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5418128/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10032-025-00540-y","type":"published","date":"2025-06-30T15:57:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":86178885,"identity":"4e37cea4-cd6b-4480-9251-95ccd273211c","added_by":"auto","created_at":"2025-07-07 16:07:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":20854736,"visible":true,"origin":"","legend":"","description":"","filename":"Squeeze.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5418128/v1_covered_894e9c14-a62e-4f52-8b67-97f465a90e60.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Character Recognition for Greek Squeezes","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":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"character recognition, squeeze, Greek, inscription","lastPublishedDoi":"10.21203/rs.3.rs-5418128/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5418128/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSqueezes are three-dimensional paper impressions made of stone inscriptions, which have to date received relatively less study than many other forms of historical documents. This paper reports on experiments in text recognition, working with a collection of approximately 30,000 squeezes originally collected from museums and archaeological sites in classical Greece. It explores a number of complementary strategies for character recognition in this medium, with the aim of establishing a strong benchmark in performance. Of the methods studied here, the best achieves a character error rate of 14%.\u003c/p\u003e","manuscriptTitle":"Character Recognition for Greek Squeezes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-27 06:52:30","doi":"10.21203/rs.3.rs-5418128/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-10T09:01:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-22T00:41:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-19T10:37:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-10T10:48:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-07T15:05:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"312819795197073697794190951665841516248","date":"2024-12-23T13:28:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"17824213237447782784405388143668811322","date":"2024-12-23T09:57:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"330870360133705721050242911215373144533","date":"2024-12-22T18:18:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247615250808804598739344311684200387433","date":"2024-12-22T16:14:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102004152716875025006022818634100998707","date":"2024-12-11T15:54:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-12-10T12:39:06+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-10T02:38:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-09T15:30:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal on Document Analysis and Recognition (IJDAR)","date":"2024-11-08T17:09:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"204a9d68-2b87-4faf-9847-30feee0ea953","owner":[],"postedDate":"November 27th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-07T15:59:44+00:00","versionOfRecord":{"articleIdentity":"rs-5418128","link":"https://doi.org/10.1007/s10032-025-00540-y","journal":{"identity":"international-journal-on-document-analysis-and-recognition-ijdar","isVorOnly":false,"title":"International Journal on Document Analysis and Recognition (IJDAR)"},"publishedOn":"2025-06-30 15:57:00","publishedOnDateReadable":"June 30th, 2025"},"versionCreatedAt":"2024-11-27 06:52:30","video":"","vorDoi":"10.1007/s10032-025-00540-y","vorDoiUrl":"https://doi.org/10.1007/s10032-025-00540-y","workflowStages":[]},"version":"v1","identity":"rs-5418128","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5418128","identity":"rs-5418128","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.