Japanese-Mobile-Receipt-OCR-1.3K: A Comprehensive Dataset Analysis and Fine-tuned Vision-Language Model for Structured Receipt Data Extraction

Japanese-Mobile-Receipt-OCR-1.3K: A Comprehensive Dataset Analysis and Fine-tuned Vision-Language Model for Structured Receipt Data Extraction | 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 Japanese-Mobile-Receipt-OCR-1.3K: A Comprehensive Dataset Analysis and Fine-tuned Vision-Language Model for Structured Receipt Data Extraction Sabari Nathan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7357197/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 We introduce Japanese-Mobile-Receipt-OCR-1.3K, a curated dataset of 1,300 real-world Japanese receipt images captured via mobile phones and annotated with 34,727 text entries. We also present a fine-tuned vision–language model for end-to-end structured receipt extraction.Our dataset analysis quantifies linguistic and layout characteristics that challenge receipt understanding. These include a heavy-tailed token length distribution (mean 9.3 tokens, maximum 255), diverse text complexity across fields, and marked heterogeneity in character composition with substantial proportions of Kanji, Kana, and numerals. We further assess semantic coverage by quantifying numeric, monetary , and temporal expressions, and measuring named entity recognition coverage across common receipt fields. Leveraging these insights, we adapt a 3B-parameter vision–language backbone to produce structured JSON outputs capturing hierarchical field relationships and standardized numeric and currency formats.Extensive experiments show consistent improvements over strong baselines. Our approach achieves notable gains in field naming consistency, hierarchical structure accuracy, and numeric formatting, alongside reductions in word error rate and character error rate.This work delivers a complete pipeline—from dataset curation and statistical analysis to model adaptation and evaluation—establishing a robust benchmark and practical methodologies for Japanese receipt understanding. Japanese receipt OCR Vision-language model Low-Rank Adaptation (LoRA) Qwen2.5-VL-3B Full Text Additional Declarations No competing interests reported. Supplementary Files sub.docx 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-7357197","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":499756409,"identity":"6fa77403-d5b9-4f01-8991-85a5eb02b7e0","order_by":0,"name":"Sabari Nathan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCElEQVRIiWNgGAWjYFACHiA2AGIJCFcORBx4QIwWHpCWAwwMxmAtCQS1MCC0JDaAePi0yLefPfi5ouCOvL1087PHH2ps0ueHHX4ItMVOTrcBuxaDM3nJkmcMnhn2yBwzNzhwLC134+00A6CWZGOzAzi0MOQYSDYYHGbskUgwkzjYcDh34+wEkJYDidtwaJHvf2P8E6jFvkci/RtQy/90w9npH/BqYbiRYwayJbFHIgdky4EEeekc/LYY3HiXZgnUktxzI6dM4syxZMMN0jkFBxIMcPtFvj/38M2GP4dt22ekb5OoqLGTl5+dvvnDhwo7OVxasNh7ABIsJAD5BlJUj4JRMApGwUgAAIzgZihgffWPAAAAAElFTkSuQmCC","orcid":"","institution":"Couger Inc","correspondingAuthor":true,"prefix":"","firstName":"Sabari","middleName":"","lastName":"Nathan","suffix":""}],"badges":[],"createdAt":"2025-08-12 15:08:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7357197/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7357197/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90787366,"identity":"22b7ab0a-0c90-4296-ac31-8e9d668addb6","added_by":"auto","created_at":"2025-09-08 07:33:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2799136,"visible":true,"origin":"","legend":"","description":"","filename":"JapanesereceiptPaper1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7357197/v1_covered_d7bebb5f-5523-471f-a851-4b8d0c4d49a6.pdf"},{"id":89047625,"identity":"75a753f6-c87b-4ec9-a76f-76bc42f6e98c","added_by":"auto","created_at":"2025-08-14 07:04:33","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":793053,"visible":true,"origin":"","legend":"","description":"","filename":"sub.docx","url":"https://assets-eu.researchsquare.com/files/rs-7357197/v1/5f41af7312f49b26a8aa434c.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Japanese-Mobile-Receipt-OCR-1.3K: A Comprehensive Dataset Analysis and Fine-tuned Vision-Language Model for Structured Receipt Data Extraction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Japanese receipt OCR, Vision-language model, Low-Rank Adaptation (LoRA), Qwen2.5-VL-3B","lastPublishedDoi":"10.21203/rs.3.rs-7357197/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7357197/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We introduce Japanese-Mobile-Receipt-OCR-1.3K, a curated dataset of 1,300 real-world Japanese receipt images captured via mobile phones and annotated with 34,727 text entries. We also present a fine-tuned vision–language model for end-to-end structured receipt extraction.Our dataset analysis quantifies linguistic and layout characteristics that challenge receipt understanding. These include a heavy-tailed token length distribution (mean 9.3 tokens, maximum 255), diverse text complexity across fields, and marked heterogeneity in character composition with substantial proportions of Kanji, Kana, and numerals. We further assess semantic coverage by quantifying numeric, monetary , and temporal expressions, and measuring named entity recognition coverage across common receipt fields. Leveraging these insights, we adapt a 3B-parameter vision–language backbone to produce structured JSON outputs capturing hierarchical field relationships and standardized numeric and currency formats.Extensive experiments show consistent improvements over strong baselines. Our approach achieves notable gains in field naming consistency, hierarchical structure accuracy, and numeric formatting, alongside reductions in word error rate and character error rate.This work delivers a complete pipeline—from dataset curation and statistical analysis to model adaptation and evaluation—establishing a robust benchmark and practical methodologies for Japanese receipt understanding.","manuscriptTitle":"Japanese-Mobile-Receipt-OCR-1.3K: A Comprehensive Dataset Analysis and Fine-tuned Vision-Language Model for Structured Receipt Data Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-14 07:04:28","doi":"10.21203/rs.3.rs-7357197/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":"76ecdef1-3aaa-4a8b-bdd3-5176a039c610","owner":[],"postedDate":"August 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-08T07:25:06+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-14 07:04:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7357197","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7357197","identity":"rs-7357197","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}