A Synthetic Text Image Generator Based on Instance Weights

A Synthetic Text Image Generator Based on Instance Weights | 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 A Synthetic Text Image Generator Based on Instance Weights Tongwei Lu, Siyang Liu, Wei Wang, Rui Zhu, Xun Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2739789/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract For scene text recognition (STR), synthetic text image generators have been successfully applied to alleviate the lack of annotated text images from the real world. However, when targeting some challenging text images, their methods have difficulty extracting foreground and background information, and the differences between the synthetic and real samples are large and difficult to adapt. In this paper, we introduce a new end-to-end synthetic text image generator, STIW, by designing a series of synthetic strategies to generate synthetic data that fit realistic text images. In addition, we propose the instantiated weights method, which connects the distributions of different domains by learning and exploiting the instance weights and the Mahalanobis distance metric. This reduces the inter-sample variation in the migration learning process of synthetic text images. Finally, we added an Attention in the LSTM of the recognition algorithm, using a mixed training learning strategy. In our experiments, our method has greater STR boosting performance than the synthetic datasets MJSynth (MJ), SynthText (ST), and SynthTIGER, and the instantiated weight method is able to further improve STR performance. Our ablation study demonstrates the benefits of using individual synthetic strategies, as well as adding to some of the problems of synthetic text image methods. text recognition Synthetic Text instance weights transfer learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-2739789","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":186677975,"identity":"09a2c9ed-48b1-41be-a32d-23929c8db190","order_by":0,"name":"Tongwei Lu","email":"","orcid":"","institution":"Hubei Key Laboratory of Intelligent Robot","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tongwei","middleName":"","lastName":"Lu","suffix":""},{"id":186677976,"identity":"1c0d3b1b-cb7e-459a-8eca-96ac147ec9a5","order_by":1,"name":"Siyang Liu","email":"","orcid":"","institution":"Hubei Key Laboratory of Intelligent Robot","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Siyang","middleName":"","lastName":"Liu","suffix":""},{"id":186677977,"identity":"10552389-1ef8-4447-aa80-e4bc16f66118","order_by":2,"name":"Wei Wang","email":"","orcid":"","institution":"Wuhan No.1 Hospital","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Wang","suffix":""},{"id":186677978,"identity":"d6b024d0-dd20-47dd-8216-74a8aea8cd2d","order_by":3,"name":"Rui Zhu","email":"","orcid":"","institution":"Hubei Key Laboratory of Intelligent Robot","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Zhu","suffix":""},{"id":186677979,"identity":"2e39842e-5d4f-4443-8d0f-aa944f8a5e1d","order_by":4,"name":"Xun Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACPmYQWcHAA6IkiNLCBtZyhoGHh3gtIIKxjYGBBC3sPGbShfMOy9gzMB+8zcNgl0eEw9jSpGduOwx0GFuyNQ9DcjERWpiPSfNuuw3UArSOh+FAYgNhLYxt0rxzQFr4vxGrBWRLA9gWNmK1gLxw7D8Pz2E2Y8s5BsmEtfDznzG8zVOTZs/e3vzwxpsKO8JaEAAcpwbEqx8Fo2AUjIJRgAcAAGLHKBgzf+pWAAAAAElFTkSuQmCC","orcid":"","institution":"Hubei Key Laboratory of Intelligent Robot","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Xun","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2023-03-27 03:29:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2739789/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2739789/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":53676180,"identity":"aebd7d1c-0a06-4152-9f38-008cf54dd2de","added_by":"auto","created_at":"2024-03-28 18:54:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":627201,"visible":true,"origin":"","legend":"","description":"","filename":"snarticletemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2739789/v1_covered_bb063768-e9be-441e-b71b-f40855b82449.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Synthetic Text Image Generator Based on Instance Weights","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"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":"text recognition, Synthetic Text, instance weights, transfer learning","lastPublishedDoi":"10.21203/rs.3.rs-2739789/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2739789/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"For scene text recognition (STR), synthetic text image generators have been successfully applied to alleviate the lack of annotated text images from the real world. However, when targeting some challenging text images, their methods have difficulty extracting foreground and background information, and the differences between the synthetic and real samples are large and difficult to adapt. In this paper, we introduce a new end-to-end synthetic text image generator, STIW, by designing a series of synthetic strategies to generate synthetic data that fit realistic text images. In addition, we propose the instantiated weights method, which connects the distributions of different domains by learning and exploiting the instance weights and the Mahalanobis distance metric. This reduces the inter-sample variation in the migration learning process of synthetic text images. Finally, we added an Attention in the LSTM of the recognition algorithm, using a mixed training learning strategy. In our experiments, our method has greater STR boosting performance than the synthetic datasets MJSynth (MJ), SynthText (ST), and SynthTIGER, and the instantiated weight method is able to further improve STR performance. Our ablation study demonstrates the benefits of using individual synthetic strategies, as well as adding to some of the problems of synthetic text image methods.","manuscriptTitle":"A Synthetic Text Image Generator Based on Instance Weights","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-03-28 06:57:17","doi":"10.21203/rs.3.rs-2739789/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":"0e40c63f-4f32-4698-a9f2-7cbfd29fd971","owner":[],"postedDate":"March 28th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-03-28T18:46:36+00:00","versionOfRecord":[],"versionCreatedAt":"2023-03-28 06:57:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2739789","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2739789","identity":"rs-2739789","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}