Innovative Approaches in Image Processing: Enhancing Feature Extraction and Recognition Capabilities

Innovative Approaches in Image Processing: Enhancing Feature Extraction and Recognition Capabilities | 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 Innovative Approaches in Image Processing: Enhancing Feature Extraction and Recognition Capabilities Zhaozhao Yang, Yuhai Yu, Yongdong Huang, Jiana Meng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5370635/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Feb, 2025 Read the published version in The Visual Computer → Version 1 posted 14 You are reading this latest preprint version Abstract This paper presents novel methods to improve feature extraction and recognition capabilities in handwritten mathematical expression recognition (HMER). By introducing a Multi-Scale Residual (MSR) module within a DenseNet encoder, we effectively capture detailed and global features across different scales, thus overcoming feature loss problems commonly encountered in HMER tasks. In addition, we propose a data augmentation strategy based on spatial transformations to increase feature diversity without additional data. Our methodology is extensively evaluated on the CROHME 2014, 2016, and 2019 datasets, achieving recognition accuracies of 56.75%, 53.79%, and 56.13%, respectively, demonstrating consistent improvements in accuracy and robustness over traditional methods. This approach further optimises the overall performance of the model, making it well-suited for real-world applications requiring high accuracy in the recognition of handwritten mathematical expressions. All source code and datasets are accessible at https://github.com/freedompuls/MsMER , facilitating reproducibility. This work advances the state of the art in HMER and provides valuable insights for researchers and practitioners in image processing and pattern recognition. handwritten mathematical expression recognition encoder-decoder multi-scale residual module data augmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Feb, 2025 Read the published version in The Visual Computer → Version 1 posted Editorial decision: Revision requested 14 Dec, 2024 Reviews received at journal 29 Nov, 2024 Reviews received at journal 20 Nov, 2024 Reviewers agreed at journal 20 Nov, 2024 Reviewers agreed at journal 20 Nov, 2024 Reviewers agreed at journal 18 Nov, 2024 Reviewers agreed at journal 18 Nov, 2024 Reviews received at journal 14 Nov, 2024 Reviewers agreed at journal 11 Nov, 2024 Reviewers agreed at journal 10 Nov, 2024 Reviewers invited by journal 04 Nov, 2024 Editor assigned by journal 01 Nov, 2024 Submission checks completed at journal 01 Nov, 2024 First submitted to journal 01 Nov, 2024 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-5370635","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":376900646,"identity":"9961f685-ad84-4278-b757-c7bd40061a3a","order_by":0,"name":"Zhaozhao Yang","email":"","orcid":"","institution":"Dalian Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Zhaozhao","middleName":"","lastName":"Yang","suffix":""},{"id":376900647,"identity":"4519716e-9f05-4399-bbcf-c1a52b065e55","order_by":1,"name":"Yuhai Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAr0lEQVRIiWNgGAWjYHACNoYPbBZglgTRWhhnsEmQqIWZhyQtBjdyzB7blEnkGRxgPnibh8Eujxgt5sY55ySKDQ6wJVvzMCQXE2WLdG6bROKGAzxm0jwMBxIbiNJiCdbC/40ELYwQW9iI0yJ55lmZZM85icSZh9mMLecYJBPWwnc8eZvEjzKbxL7jzQ9vvKmwI6xF4QCHAYTFDHYnIfVAIN/A/oAIZaNgFIyCUTCiAQCAHTiHl3mDfwAAAABJRU5ErkJggg==","orcid":"","institution":"Dalian Minzu University","correspondingAuthor":true,"prefix":"","firstName":"Yuhai","middleName":"","lastName":"Yu","suffix":""},{"id":376900648,"identity":"c4c4c70e-f66a-45b1-af7d-e6681e1cda1e","order_by":2,"name":"Yongdong Huang","email":"","orcid":"","institution":"Dalian Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Yongdong","middleName":"","lastName":"Huang","suffix":""},{"id":376900649,"identity":"226bf0d1-bd50-40ec-b452-4369a2d30afc","order_by":3,"name":"Jiana Meng","email":"","orcid":"","institution":"Dalian Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Jiana","middleName":"","lastName":"Meng","suffix":""}],"badges":[],"createdAt":"2024-11-01 05:08:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5370635/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5370635/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00371-025-03830-y","type":"published","date":"2025-02-27T15:57:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":77622682,"identity":"ea2ee597-434a-4bbc-b273-3e96c8f26468","added_by":"auto","created_at":"2025-03-03 16:09:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":799986,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5370635/v1_covered_8452804f-49eb-4078-a60f-9ae12b468f65.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Innovative Approaches in Image Processing: Enhancing Feature Extraction and Recognition Capabilities","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"handwritten mathematical expression recognition, encoder-decoder, multi-scale residual module, data augmentation","lastPublishedDoi":"10.21203/rs.3.rs-5370635/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5370635/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents novel methods to improve feature extraction and recognition capabilities in handwritten mathematical expression recognition (HMER). By introducing a Multi-Scale Residual (MSR) module within a DenseNet encoder, we effectively capture detailed and global features across different scales, thus overcoming feature loss problems commonly encountered in HMER tasks. In addition, we propose a data augmentation strategy based on spatial transformations to increase feature diversity without additional data. Our methodology is extensively evaluated on the CROHME 2014, 2016, and 2019 datasets, achieving recognition accuracies of 56.75%, 53.79%, and 56.13%, respectively, demonstrating consistent improvements in accuracy and robustness over traditional methods. This approach further optimises the overall performance of the model, making it well-suited for real-world applications requiring high accuracy in the recognition of handwritten mathematical expressions. All source code and datasets are accessible at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/freedompuls/MsMER\u003c/span\u003e\u003cspan address=\"https://github.com/freedompuls/MsMER\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e, facilitating reproducibility. This work advances the state of the art in HMER and provides valuable insights for researchers and practitioners in image processing and pattern recognition.\u003c/p\u003e","manuscriptTitle":"Innovative Approaches in Image Processing: Enhancing Feature Extraction and Recognition Capabilities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-13 04:59:30","doi":"10.21203/rs.3.rs-5370635/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-14T17:20:11+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-29T12:04:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-21T01:12:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135987018212123395729684040054920779022","date":"2024-11-20T10:25:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"175661882488090016754108413387728254084","date":"2024-11-20T10:06:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152249579632375230453113117411173506619","date":"2024-11-18T15:53:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"262844263609078019189958197881546741577","date":"2024-11-18T10:30:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-14T05:31:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324282953271666330320478638633033408390","date":"2024-11-12T01:35:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"106839746127776310502054253124769373538","date":"2024-11-10T09:39:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-04T08:56:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-01T20:05:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-01T15:14:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2024-11-01T04:55:52+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"587fe61a-97df-43c3-bd27-c6ab595a5876","owner":[],"postedDate":"November 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-03-03T16:03:56+00:00","versionOfRecord":{"articleIdentity":"rs-5370635","link":"https://doi.org/10.1007/s00371-025-03830-y","journal":{"identity":"the-visual-computer","isVorOnly":false,"title":"The Visual Computer"},"publishedOn":"2025-02-27 15:57:23","publishedOnDateReadable":"February 27th, 2025"},"versionCreatedAt":"2024-11-13 04:59:30","video":"","vorDoi":"10.1007/s00371-025-03830-y","vorDoiUrl":"https://doi.org/10.1007/s00371-025-03830-y","workflowStages":[]},"version":"v1","identity":"rs-5370635","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5370635","identity":"rs-5370635","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}