Scene Text Detection Using Attention with Depthwise Separable Convolutions for Mobile Applications

Scene Text Detection Using Attention with Depthwise Separable Convolutions for Mobile Applications | 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 Scene Text Detection Using Attention with Depthwise Separable Convolutions for Mobile Applications Ramalakshmi Subbukalai, Vani Vijayan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7487631/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Jan, 2026 Read the published version in Journal of Signal Processing Systems → Version 1 posted You are reading this latest preprint version Abstract Text detection from images or videos contributes well in many applications since deep-learned features can effectively capture textual cues. However, many existing methods give average performance when they are applied to detect Arbitrary-shaped text present in the image. This limitation is mainly due to the constraints of their text representations, which include horizontal boxes, rotating rectangles, and quadrangles. This paper proposes a Deep-Learned Fusion Attention Network (DLFANet) for learning the prominent features of arbitrary shaped text by using a lightweight network known as shared network which is further fine-tuned by the proposed Feature Attention Module Enhancement (FAME). In addition, the Final Feature Module (FFM) with an Attention Detection Head (ADH) and Geometry Aware Pixel Network (GAPN) are used to detect the location of the text effectively. The performance analysis of the proposed work on standard datasets Total-Text, CTW 1500, and ICDAR 2015 gives better results when compared to other state-of-the-art algorithms. Text detection Feature Attention Module Enhancement Deep-Learned Fusion Attention Network Attention Detection Head Final Feature Module Geometry Aware Pixel Network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Jan, 2026 Read the published version in Journal of Signal Processing Systems → 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-7487631","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":510256859,"identity":"ca039bb3-d472-4f47-8edb-4d42d0e742c4","order_by":0,"name":"Ramalakshmi Subbukalai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABVklEQVRIie2QMWvCQBTHLwhOhtvkiW39CleE6iD4Vd5DsIsphS4ZCk0R4tR2VUL7BboEAsFuKYEujbhGdFAKboFAodjF9kKhKIrgVkp+3HDv/vfjvTvGUlL+KlOGTDDFkMtjwDIGQ712xZMIz7cruK7IDQZNLBhJJHYpkl9FMX0UXnK0qVQ6rxTjZbNeyfvtd7U/oV7n+TqeZjNn5eEjxVPBSjzvrSoHgeYAvrToySKzqAZzsnLUBsxlL07CSEaCHfcsXFWAaTZgVkcxJjOjmj49MDIAIae44cBOFBmtKzxyFrjU61KRgyUKn7UXKEBxugMZbVFAc4HMlmKPySgmiiVLQBRk8xt3axeI3CrdNkkqZuE+mJd73ZlZRQ/LEKpuVbbbeAvXnDD+aMjBTt/iqD857A4b/uhz+XXE7wbOaKHXSry4puwC8OeD9oB7+9xOSUlJ+b98AwTtjd+fVFLxAAAAAElFTkSuQmCC","orcid":"","institution":"National Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Ramalakshmi","middleName":"","lastName":"Subbukalai","suffix":""},{"id":510256860,"identity":"5669913d-639b-4747-86a4-95652e28c213","order_by":1,"name":"Vani Vijayan","email":"","orcid":"","institution":"National Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Vani","middleName":"","lastName":"Vijayan","suffix":""}],"badges":[],"createdAt":"2025-08-29 10:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7487631/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7487631/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11265-025-01981-8","type":"published","date":"2026-01-21T15:57:15+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":101152071,"identity":"4fb71587-e4da-4173-a05a-09178d5a2bd6","added_by":"auto","created_at":"2026-01-26 16:10:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1666078,"visible":true,"origin":"","legend":"","description":"","filename":"RamalakshmiSubbukalai4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7487631/v1_covered_e15657e9-c3c9-47c3-a3d1-411f85a68703.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Scene Text Detection Using Attention with Depthwise Separable Convolutions for Mobile Applications","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":true,"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 detection, Feature Attention Module Enhancement, Deep-Learned Fusion Attention Network, Attention Detection Head, Final Feature Module, Geometry Aware Pixel Network","lastPublishedDoi":"10.21203/rs.3.rs-7487631/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7487631/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eText detection from images or videos contributes well in many applications since deep-learned features can effectively capture textual cues. However, many existing methods give average performance when they are applied to detect Arbitrary-shaped text present in the image. This limitation is mainly due to the constraints of their text representations, which include horizontal boxes, rotating rectangles, and quadrangles. This paper proposes a Deep-Learned Fusion Attention Network (DLFANet) for learning the prominent features of arbitrary shaped text by using a lightweight network known as shared network which is further fine-tuned by the proposed Feature Attention Module Enhancement (FAME). In addition, the Final Feature Module (FFM) with an Attention Detection Head (ADH) and Geometry Aware Pixel Network (GAPN) are used to detect the location of the text effectively. The performance analysis of the proposed work on standard datasets Total-Text, CTW 1500, and ICDAR 2015 gives better results when compared to other state-of-the-art algorithms.\u003c/p\u003e","manuscriptTitle":"Scene Text Detection Using Attention with Depthwise Separable Convolutions for Mobile Applications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 17:51:56","doi":"10.21203/rs.3.rs-7487631/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":"a46f0700-4bc3-44df-8e5f-d63c6aee2d68","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-26T16:06:50+00:00","versionOfRecord":{"articleIdentity":"rs-7487631","link":"https://doi.org/10.1007/s11265-025-01981-8","journal":{"identity":"journal-of-signal-processing-systems","isVorOnly":false,"title":"Journal of Signal Processing Systems"},"publishedOn":"2026-01-21 15:57:15","publishedOnDateReadable":"January 21st, 2026"},"versionCreatedAt":"2025-09-11 17:51:56","video":"","vorDoi":"10.1007/s11265-025-01981-8","vorDoiUrl":"https://doi.org/10.1007/s11265-025-01981-8","workflowStages":[]},"version":"v1","identity":"rs-7487631","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7487631","identity":"rs-7487631","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}