Improved CTPN and CRNN for blind reading based on attention mechanism and feature fusion

Improved CTPN and CRNN for blind reading based on attention mechanism and feature fusion | 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 Improved CTPN and CRNN for blind reading based on attention mechanism and feature fusion Xin Jin, Pengfei Wang, Chuntian Gong, Lijun Wang, Bingxue Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6000342/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 19 You are reading this latest preprint version Abstract The primary function of a blind reader is to convert visual information into speech, thereby enabling blind individuals to access printed or electronic text content. Current blind reader technologies predominantly rely on online detection and recognition, which necessitates the use of cloud platforms. In this research, we present a blind reader technology that enhances the CTPN detection and CRNN identification algorithms, both of which are implemented on the Raspberry Pi 4B development board. This system is capable of performing text detection and recognition tasks in a completely offline environment. On the ICDAR2015 dataset, the enhanced CTPN model outperformed the original CTPN model in terms of accuracy, recall, and F-value, with improvements of 8.0%, 6.7%, and 10.1%, respectively. Similarly, on the ICDAR2017 RCTW dataset, the upgraded CRNN model surpassed the original CRNN model by 5%. The experimental results indicate that the Raspberry Pi-based blind reader technology proposed in this research can effectively assist blind individuals in reading books, achieving reasonably high levels of detection and recognition accuracy. Physical sciences/Engineering Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Mathematics and computing/Software Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 18 May, 2026 Reviews received at journal 22 Mar, 2026 Reviews received at journal 21 Mar, 2026 Reviews received at journal 15 Mar, 2026 Reviews received at journal 13 Mar, 2026 Reviewers agreed at journal 08 Mar, 2026 Reviewers agreed at journal 07 Mar, 2026 Reviewers agreed at journal 07 Mar, 2026 Reviews received at journal 07 Mar, 2026 Reviewers agreed at journal 07 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 04 Mar, 2026 Editor assigned by journal 04 Jul, 2025 Editor invited by journal 26 Jun, 2025 Reviews received at journal 27 Apr, 2025 Reviewers agreed at journal 14 Apr, 2025 Reviewers invited by journal 12 Apr, 2025 Submission checks completed at journal 10 Apr, 2025 First submitted to journal 31 Mar, 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-6000342","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":442832089,"identity":"8d176237-d351-4889-9077-3fd028433d35","order_by":0,"name":"Xin Jin","email":"","orcid":"","institution":"Liaoning Petrochemical Unversity","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Jin","suffix":""},{"id":442832092,"identity":"103640e8-5f22-42b7-843a-1377cbf0d549","order_by":1,"name":"Pengfei Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3ElEQVRIiWNgGAWjYNACGwkefvbmAwc+/CBaS5qNnGTPscSDM3uI15JmbHDDx/gwBxsRig2Onz38uiDhcGLDDZ4Phxl4GOT5xQ4Q0HImL816BlBL4+zeDYcLLBgMZ85OwK/F7ECOmTHvj8OJzTJnNxyewcOQYHCbkJbzb8yMeYC2tEnkPDjMw0aMlhs5xo95EtKMeSRyGIjTYn/jjRnzjAQbOQmeYwbAQJYg7BfJ/hzjzwUJEjz2x5sff/jww0aeX5qAFiBgk0biSBBUDgLMn4lSNgpGwSgYBSMXAAAgckrUIsPMcwAAAABJRU5ErkJggg==","orcid":"","institution":"Liaoning Petrochemical Unversity","correspondingAuthor":true,"prefix":"","firstName":"Pengfei","middleName":"","lastName":"Wang","suffix":""},{"id":442832095,"identity":"3a0d496d-6a37-4506-804f-386768620b67","order_by":2,"name":"Chuntian Gong","email":"","orcid":"","institution":"Liaoning Petrochemical Unversity","correspondingAuthor":false,"prefix":"","firstName":"Chuntian","middleName":"","lastName":"Gong","suffix":""},{"id":442832097,"identity":"39bfc52a-d5b0-4c37-9655-9a1386f331c1","order_by":3,"name":"Lijun Wang","email":"","orcid":"","institution":"Neusoft Group Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Lijun","middleName":"","lastName":"Wang","suffix":""},{"id":442832098,"identity":"71c2f556-0f07-4341-a461-ac6d09305d2a","order_by":4,"name":"Bingxue Wang","email":"","orcid":"","institution":"Liaoning Petrochemical Unversity","correspondingAuthor":false,"prefix":"","firstName":"Bingxue","middleName":"","lastName":"Wang","suffix":""},{"id":442832099,"identity":"0324ac51-c2b7-4f7e-8de0-d07ccbcc787c","order_by":5,"name":"Ziqian Li","email":"","orcid":"","institution":"Liaoning Petrochemical Unversity","correspondingAuthor":false,"prefix":"","firstName":"Ziqian","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-02-10 15:08:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6000342/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6000342/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[],"financialInterests":"No competing interests reported.","formattedTitle":"Improved CTPN and CRNN for blind reading based on attention mechanism and feature fusion","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":false,"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-6000342/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6000342/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe primary function of a blind reader is to convert visual information into speech, thereby enabling blind individuals to access printed or electronic text content. Current blind reader technologies predominantly rely on online detection and recognition, which necessitates the use of cloud platforms. In this research, we present a blind reader technology that enhances the CTPN detection and CRNN identification algorithms, both of which are implemented on the Raspberry Pi 4B development board. This system is capable of performing text detection and recognition tasks in a completely offline environment. On the ICDAR2015 dataset, the enhanced CTPN model outperformed the original CTPN model in terms of accuracy, recall, and F-value, with improvements of 8.0%, 6.7%, and 10.1%, respectively. Similarly, on the ICDAR2017 RCTW dataset, the upgraded CRNN model surpassed the original CRNN model by 5%. The experimental results indicate that the Raspberry Pi-based blind reader technology proposed in this research can effectively assist blind individuals in reading books, achieving reasonably high levels of detection and recognition accuracy.\u003c/p\u003e","manuscriptTitle":"Improved CTPN and CRNN for blind reading based on attention mechanism and feature fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-15 14:47:01","doi":"10.21203/rs.3.rs-6000342/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-18T13:51:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-22T12:53:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-21T07:31:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-15T09:08:39+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-13T09:35:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"133261486618544943175812642263546111454","date":"2026-03-08T06:14:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"107460267869932911622145920082116366907","date":"2026-03-07T17:41:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"291599899777851139189849278401761193240","date":"2026-03-07T17:04:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T10:00:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"312259341908292864868024439285316658034","date":"2026-03-07T09:46:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"295232529936092804202326929474312654016","date":"2026-03-05T07:50:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"268814861679845015680670087460012091300","date":"2026-03-04T21:16:50+00:00","index":"hide","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-04T11:15:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-26T04:37:28+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-27T11:49:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338762057886413729883762763357593273332","date":"2025-04-14T16:20:57+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-12T12:00:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-10T11:39:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-31T18:16:50+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":"755060e0-3c5e-4480-a38b-ebeaf39262fe","owner":[],"postedDate":"April 15th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-18T13:51:37+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":47144919,"name":"Physical sciences/Engineering"},{"id":47144920,"name":"Physical sciences/Mathematics and computing"},{"id":47144921,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":47144922,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":47144923,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2026-05-18T13:55:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-15 14:47:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6000342","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6000342","identity":"rs-6000342","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}