Image Detection and Data extraction Using Hybrid Deep Learning Techniques

Image Detection and Data extraction Using Hybrid Deep Learning Techniques | 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 Image Detection and Data extraction Using Hybrid Deep Learning Techniques R V Raghavendra Rao, Ch. Ram Mohan Reddy, Vishruth AC, Prajwal P K This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7065509/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 In the current age of data, numerous pictures are everywhere that permit the extraction of text and certain image-based information. There are several technologies/ tools that can be used to accomplish this task. Optical Character Recognition (OCR) is a vital technology to automate text extraction from pictures, specifically for identifying people through Identification cards. This paper introduces a hybrid system that integrates few conventional OCR utilities such as PyTesseract with deep learning algorithms, including Mask Region-based Convolutional Neural Networks (R-CNN) for object detection and Convolutional Recurrent Neural Network (CRNN) for text recognition. The system also boosts the text extraction with the application of sophisticated preprocessing techniques such as noise removal, binarization, and edge detection, which enhance image quality and recognition accuracy. After the text is extracted, the text extracted is well-arranged and stored in an Excel file to make it convenient to store and retrieve. The system is compared with the general traditional OCR systems, and that the system demonstrates improvements in accuracy rate, speed of processing, and error correction, Also even under difficult conditions such as low-resolution images and varying lighting. The suggested system is ideal for verification of identities in the majority of the sectors like banking, government, and education. The future developments will involve support for multi-languages and compatibility with mobile devices so that the system becomes even more efficient and versatile with user-friendly. Optical Character Recognition PyTesseract Mask R-CNN CRNN Deep Learning Text Extraction 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-7065509","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":489026373,"identity":"3fb1a265-1a35-425a-9e3b-dfe7c14992ea","order_by":0,"name":"R V Raghavendra Rao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYPACmwQ4k41ILWmkazmcQEgFApjPPsC64UfN+Tzd/sMPHzDU2DHwSTfg1yJzLoHtZs+x28VmN9KMDRiOJTOwyRzAr0WCh4HtNhAlbrvBwybBwHaAgU2CgCMhWv6dS9x2/gz7D4Z/xGphbDuQuO1ADhsDkEGMFsa2m719yWC/SCT2JfMQoYX52I0f3+zyzM4ffvjhwzc7OfkZBLQwMDA2INhAxTyE1I+CUTAKRsEoIAIAACdEPIFq81owAAAAAElFTkSuQmCC","orcid":"","institution":"BMS College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"R","middleName":"V Raghavendra","lastName":"Rao","suffix":""},{"id":489026374,"identity":"17d8ef0a-d83b-4f94-ab61-02803cd84d37","order_by":1,"name":"Ch. Ram Mohan Reddy","email":"","orcid":"","institution":"BMS College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Ch.","middleName":"Ram Mohan","lastName":"Reddy","suffix":""},{"id":489026375,"identity":"f6eda3d4-13a5-49a6-89e1-30a4a8243861","order_by":2,"name":"Vishruth AC","email":"","orcid":"","institution":"BMS College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Vishruth","middleName":"","lastName":"AC","suffix":""},{"id":489026376,"identity":"c83f3820-5b27-458c-bf06-ce0b45eefbe6","order_by":3,"name":"Prajwal P K","email":"","orcid":"","institution":"BMS College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Prajwal","middleName":"P","lastName":"K","suffix":""}],"badges":[],"createdAt":"2025-07-07 12:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7065509/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7065509/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91930641,"identity":"8b19cac2-d8ac-44b7-8d94-861b99beab73","added_by":"auto","created_at":"2025-09-23 02:26:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":600165,"visible":true,"origin":"","legend":"","description":"","filename":"ImageDetectionandDataextractionUsingHybridDeepLearningTechniques.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7065509/v1_covered_1a882fe4-63e8-4913-af46-1ca02ef5fede.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Image Detection and Data extraction Using Hybrid Deep Learning Techniques","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":"Optical Character Recognition, PyTesseract, Mask R-CNN, CRNN, Deep Learning, Text Extraction","lastPublishedDoi":"10.21203/rs.3.rs-7065509/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7065509/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the current age of data, numerous pictures are everywhere that permit the extraction of text and certain image-based information. There are several technologies/ tools that can be used to accomplish this task. Optical Character Recognition (OCR) is a vital technology to automate text extraction from pictures, specifically for identifying people through Identification cards. This paper introduces a hybrid system that integrates few conventional OCR utilities such as PyTesseract with deep learning algorithms, including Mask Region-based Convolutional Neural Networks (R-CNN) for object detection and Convolutional Recurrent Neural Network (CRNN) for text recognition. The system also boosts the text extraction with the application of sophisticated preprocessing techniques such as noise removal, binarization, and edge detection, which enhance image quality and recognition accuracy. After the text is extracted, the text extracted is well-arranged and stored in an Excel file to make it convenient to store and retrieve. The system is compared with the general traditional OCR systems, and that the system demonstrates improvements in accuracy rate, speed of processing, and error correction, Also even under difficult conditions such as low-resolution images and varying lighting. The suggested system is ideal for verification of identities in the majority of the sectors like banking, government, and education. The future developments will involve support for multi-languages and compatibility with mobile devices so that the system becomes even more efficient and versatile with user-friendly.","manuscriptTitle":"Image Detection and Data extraction Using Hybrid Deep Learning Techniques","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-24 03:32:06","doi":"10.21203/rs.3.rs-7065509/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":"ffa2594b-d773-42b9-8b88-7a7678209ad7","owner":[],"postedDate":"July 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-23T02:25:21+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-24 03:32:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7065509","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7065509","identity":"rs-7065509","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}