VI-OCR: "Visually Impaired" Optical Character Recognition Pipeline for Text Accessibility Assessment

VI-OCR: "Visually Impaired" Optical Character Recognition Pipeline for Text Accessibility Assessment | 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 Article VI-OCR: "Visually Impaired" Optical Character Recognition Pipeline for Text Accessibility Assessment Qingying Gao, Roberto Manduchi, Pradeep Ramulu, Gordon Legge, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7032700/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Low vision adversely impacts daily activities, particularly reading. However, quantifying text accessibility for different levels of low vision is challenging, leading to product designs that often overlook the vision status of low vision readers. In this paper, we bridge the gap between computer vision and low vision fields by introducing a text accessibility assessment pipeline called VI-OCR (short for Visually Impaired Optical Character Recognition), based on state-of-the-art OCR models. VI-OCR mimics human text recognition ability under specified levels of visual acuity and contrast sensitivity loss, to estimate whether text of a given size would be recognizable for a low vision human reader. We benchmarked specialized OCR models and vision-language models in replicating text recognition performances with visual acuity and contrast sensitivity deficits across three reading tasks: letter acuity using ETDRS charts, word acuity using MNREAD charts, and scene text recognition using complex real-life images. Comparing model performance to that of normal vision participants on degraded texts revealed major issues in some models including limited generalizability across reading tasks, difficulties dealing with severe contrast reduction, and overperforming rather than mimicking human observers. However, robust human-like performance of winning models such as Qwen and Gemini supports the feasibility of VI-OCR in assessing text accessibility. Health sciences/Health care Physical sciences/Mathematics and computing Biological sciences/Neuroscience Full Text Additional Declarations No competing interests reported. Supplementary Files VIOCRsupplementary.docx Cite Share Download PDF Status: Published Journal Publication published 11 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 29 Aug, 2025 Reviews received at journal 24 Aug, 2025 Reviewers agreed at journal 16 Aug, 2025 Reviewers agreed at journal 13 Aug, 2025 Reviews received at journal 11 Aug, 2025 Reviewers agreed at journal 11 Aug, 2025 Reviewers invited by journal 11 Aug, 2025 Editor assigned by journal 11 Aug, 2025 Editor invited by journal 11 Jul, 2025 Submission checks completed at journal 09 Jul, 2025 First submitted to journal 09 Jul, 2025 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-7032700","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":490027574,"identity":"f9ff7447-e9c7-4fb1-9fa7-e6439d62b555","order_by":0,"name":"Qingying Gao","email":"","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":false,"prefix":"","firstName":"Qingying","middleName":"","lastName":"Gao","suffix":""},{"id":490027576,"identity":"dac77f65-2540-431f-aec5-f1d234c58147","order_by":1,"name":"Roberto Manduchi","email":"","orcid":"","institution":"University of California, Santa Cruz","correspondingAuthor":false,"prefix":"","firstName":"Roberto","middleName":"","lastName":"Manduchi","suffix":""},{"id":490027578,"identity":"27e1a3b8-e6ad-4942-9918-1be4b04f90f3","order_by":2,"name":"Pradeep Ramulu","email":"","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":false,"prefix":"","firstName":"Pradeep","middleName":"","lastName":"Ramulu","suffix":""},{"id":490027581,"identity":"7fce9169-5b76-431b-8ac2-b247acd73fff","order_by":3,"name":"Gordon Legge","email":"","orcid":"","institution":"University of Minnesota","correspondingAuthor":false,"prefix":"","firstName":"Gordon","middleName":"","lastName":"Legge","suffix":""},{"id":490027582,"identity":"e86de4e2-3eb2-4d14-a7aa-0a1d91ca8f18","order_by":4,"name":"Yingzi Xiong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYFACxgYgUSPHz3AGSLMRr+WYsWQD8VrAgDnR4AAPkVoMbiQ3Pi74xZZgfPDsAYYPZYeJ0HLmYLPxzD6ZPLMD5xIYZ5wjRsvxxjZp3h62YrMDZwyYeduI0XKYEaSFOXFzA1DLX6K0gGzh+cGcuIEBqIWRGC2SIL/wNhwzlgA67GDPuXTCWvhupD98zPMHGJUzzhg++FFmTViLwgEgwdgGJCQOMBwgrB4I5BtA5B8g5m8gSsMoGAWjYBSMQAAAt1tCPm4dhJgAAAAASUVORK5CYII=","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":true,"prefix":"","firstName":"Yingzi","middleName":"","lastName":"Xiong","suffix":""}],"badges":[],"createdAt":"2025-07-02 22:08:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7032700/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7032700/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-30982-7","type":"published","date":"2025-12-11T15:56:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98243626,"identity":"8a272261-9f8e-4428-a80e-139a75085d61","added_by":"auto","created_at":"2025-12-15 16:09:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1868373,"visible":true,"origin":"","legend":"","description":"","filename":"ftmbgpntdxhnprtpbmjjvjxprwrtnwrr.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7032700/v1_covered_e2aa2b03-e7c7-4f10-84e4-823d9d402df7.pdf"},{"id":87542526,"identity":"c275803e-f5b9-4fdb-887a-4836e5a056b0","added_by":"auto","created_at":"2025-07-25 03:57:11","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":2102508,"visible":true,"origin":"","legend":"","description":"","filename":"VIOCRsupplementary.docx","url":"https://assets-eu.researchsquare.com/files/rs-7032700/v1/e151c9f73edb814463f4d427.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"VI-OCR: \"Visually Impaired\" Optical Character Recognition Pipeline for Text Accessibility Assessment","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7032700/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7032700/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Low vision adversely impacts daily activities, particularly reading. However, quantifying text accessibility for different levels of low vision is challenging, leading to product designs that often overlook the vision status of low vision readers. In this paper, we bridge the gap between computer vision and low vision fields by introducing a text accessibility assessment pipeline called VI-OCR (short for Visually Impaired Optical Character Recognition), based on state-of-the-art OCR models. VI-OCR mimics human text recognition ability under specified levels of visual acuity and contrast sensitivity loss, to estimate whether text of a given size would be recognizable for a low vision human reader. We benchmarked specialized OCR models and vision-language models in replicating text recognition performances with visual acuity and contrast sensitivity deficits across three reading tasks: letter acuity using ETDRS charts, word acuity using MNREAD charts, and scene text recognition using complex real-life images. Comparing model performance to that of normal vision participants on degraded texts revealed major issues in some models including limited generalizability across reading tasks, difficulties dealing with severe contrast reduction, and overperforming rather than mimicking human observers. However, robust human-like performance of winning models such as Qwen and Gemini supports the feasibility of VI-OCR in assessing text accessibility. ","manuscriptTitle":"VI-OCR: \"Visually Impaired\" Optical Character Recognition Pipeline for Text Accessibility Assessment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-25 03:57:06","doi":"10.21203/rs.3.rs-7032700/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-29T07:06:07+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-24T10:53:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324388976319071813496721960337713556934","date":"2025-08-16T07:43:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232472831367017472843192016623628120655","date":"2025-08-13T14:55:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-11T16:59:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"272331943646880991520310605415764271428","date":"2025-08-11T16:23:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-11T15:33:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-11T13:16:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-11T06:28:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-09T17:11:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-07-09T17:09:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"99b6d02e-5507-4561-bf10-d87720f65cde","owner":[],"postedDate":"July 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":52026306,"name":"Health sciences/Health care"},{"id":52026307,"name":"Physical sciences/Mathematics and computing"},{"id":52026308,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2025-12-15T16:02:04+00:00","versionOfRecord":{"articleIdentity":"rs-7032700","link":"https://doi.org/10.1038/s41598-025-30982-7","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-11 15:56:59","publishedOnDateReadable":"December 11th, 2025"},"versionCreatedAt":"2025-07-25 03:57:06","video":"","vorDoi":"10.1038/s41598-025-30982-7","vorDoiUrl":"https://doi.org/10.1038/s41598-025-30982-7","workflowStages":[]},"version":"v1","identity":"rs-7032700","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7032700","identity":"rs-7032700","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}