Lightweight Real-Time Image Captioning for Mobile Systems: An Optimized Multimodal Framework and Benchmarking Study

Lightweight Real-Time Image Captioning for Mobile Systems: An Optimized Multimodal Framework and Benchmarking Study | 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 Lightweight Real-Time Image Captioning for Mobile Systems: An Optimized Multimodal Framework and Benchmarking Study othmane sebban, ahmed azough, Mohamed Lamrini This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9404266/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 13 You are reading this latest preprint version Abstract Visually impaired people continue to face barriers in accessing written and audio content. To address this, we propose a comparative study of advanced technological solutions that enhance autonomy and environmental interaction. We utilize deep learning models, including InceptionV3, InceptionV4, and ResNet50, in conjunction with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) decoders. These models are trained on the MSCOCO 2017 dataset. Integrated OCR, translation, and speech synthesis modules improve visual recognition and multilingual accessibility. A mobile application combines these features for real-time interaction. Evaluation utilizes a structured framework that encompasses accuracy, responsiveness, ergonomics, robustness, and adaptability. The proposed system achieves an overall accuracy of 92.6%, outperforming baseline configurations and demonstrating its effectiveness for real-time assistive applications. These findings confirm the feasibility of efficient multimodal assistive systems for real-world mobile accessibility. Deep Learning Visual Assistance Systems Real-Time Captioning Usability Evaluation System Benchmarking Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 17 May, 2026 Reviews received at journal 09 May, 2026 Reviews received at journal 09 May, 2026 Reviews received at journal 08 May, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 21 Apr, 2026 Reviewers agreed at journal 17 Apr, 2026 Reviewers agreed at journal 16 Apr, 2026 Reviewers agreed at journal 16 Apr, 2026 Reviewers invited by journal 16 Apr, 2026 Editor assigned by journal 16 Apr, 2026 Submission checks completed at journal 16 Apr, 2026 First submitted to journal 13 Apr, 2026 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-9404266","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":627601713,"identity":"ee70222e-85a9-46f3-bce1-fed0171ac6e4","order_by":0,"name":"othmane sebban","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYFACHjiDDUjYIIvgAGyoWtJI13KYsBZ++d6jG37usGGQb+899uDnjvOJ86edPfiBocaOQbf9AFYtkm18aTd7z6QxGJw5l27Ye+Z24obbeckSDMeSGczOJGDVYnCMx+wGb9thBgOJHDMJ3jagFukcAwkGtgMMZgdwa7n5t+0/g/z8N2aSf9vOJc6fnWP8g+EfUMv5Bzi13OZtA7r6Bo+ZNJCR2HAbaB0jUMTsBnZbJNtyzG7LtiXzGJzJSzcGMoyBfkmzSOxLBjoYuy38zGfMbr5ts5OTbz977CGQITt/du7hGx++2cmZncduCwygxUUC4QgdBaNgFIyCUYAHAADh4mA5CxL3vgAAAABJRU5ErkJggg==","orcid":"","institution":"Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University","correspondingAuthor":true,"prefix":"","firstName":"othmane","middleName":"","lastName":"sebban","suffix":""},{"id":627601714,"identity":"b32649a3-704d-4210-97ba-f9cd9e02089e","order_by":1,"name":"ahmed azough","email":"","orcid":"","institution":"De Vinci Higher Education, De Vinci Research Center","correspondingAuthor":false,"prefix":"","firstName":"ahmed","middleName":"","lastName":"azough","suffix":""},{"id":627601715,"identity":"f639c361-4cf2-4a16-8753-ca22f7b38d23","order_by":2,"name":"Mohamed Lamrini","email":"","orcid":"","institution":"Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University","correspondingAuthor":false,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Lamrini","suffix":""}],"badges":[],"createdAt":"2026-04-13 12:41:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9404266/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9404266/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107706968,"identity":"bd83e815-3aaf-4fbb-8def-2ccd710abf87","added_by":"auto","created_at":"2026-04-24 09:19:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1788259,"visible":true,"origin":"","legend":"","description":"","filename":"LightweightRealTimeImageCaptioningforMobileSystemsAnOptimizedMultimodalFrameworkandBenchmarkingStudy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9404266/v1_covered_695dbe91-bb91-454c-a2ce-04db2b32616f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight Real-Time Image Captioning for Mobile Systems: An Optimized Multimodal Framework and Benchmarking Study","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":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Deep Learning, Visual Assistance Systems, Real-Time Captioning, Usability Evaluation, System Benchmarking","lastPublishedDoi":"10.21203/rs.3.rs-9404266/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9404266/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Visually impaired people continue to face barriers in accessing written and audio content. To address this, we propose a comparative study of advanced technological solutions that enhance autonomy and environmental interaction. We utilize deep learning models, including InceptionV3, InceptionV4, and ResNet50, in conjunction with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) decoders. These models are trained on the MSCOCO 2017 dataset. Integrated OCR, translation, and speech synthesis modules improve visual recognition and multilingual accessibility. A mobile application combines these features for real-time interaction. Evaluation utilizes a structured framework that encompasses accuracy, responsiveness, ergonomics, robustness, and adaptability. The proposed system achieves an overall accuracy of 92.6\\%, outperforming baseline configurations and demonstrating its effectiveness for real-time assistive applications. These findings confirm the feasibility of efficient multimodal assistive systems for real-world mobile accessibility.","manuscriptTitle":"Lightweight Real-Time Image Captioning for Mobile Systems: An Optimized Multimodal Framework and Benchmarking Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-23 12:12:14","doi":"10.21203/rs.3.rs-9404266/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-18T02:09:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T09:25:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T07:09:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-08T16:08:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"280746474211663258512608435637976150115","date":"2026-04-22T03:09:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"33627703009359090413642937013911809151","date":"2026-04-22T02:59:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"208714431125870920867088931558794223598","date":"2026-04-17T05:44:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"76079565892140165417348778209239144445","date":"2026-04-17T02:20:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"256626838117844873359327005704590021441","date":"2026-04-17T01:59:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-17T00:56:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-16T14:46:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-16T08:36:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Real-Time Image Processing","date":"2026-04-13T12:35:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e9391bca-f1ff-441b-a1b8-ceaef0aa101c","owner":[],"postedDate":"April 23rd, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-18T02:09:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T09:25:19+00:00","index":65,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T07:09:26+00:00","index":64,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-08T16:08:50+00:00","index":63,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T02:23:29+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-23 12:12:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9404266","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9404266","identity":"rs-9404266","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}