Research on Fish Otolith Image Recognition Enhanced by EfficientNet

Research on Fish Otolith Image Recognition Enhanced by EfficientNet | 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 Article Research on Fish Otolith Image Recognition Enhanced by EfficientNet XIAO GU, Aihuan Song, Yingjun Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8109572/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Fish otolith identification is of great significance for the species recognition and scientific management of fishery resources. Traditional methods for otolith identification are highly dependent on expert experience, and the process is cumbersome and subjective. In addition, factors such as limited sample sizes and the subtle, difficult-to-distinguish features of otoliths lead to unsatisfactory identification performance. To this end, this paper proposes a lightweight EfficientNet-based framework that integrates data augmentation and texture feature optimization for otolith image classification. This approach significantly reduces model parameters and computational cost while maintaining classification accuracy. Experimental results demonstrate that the proposed model achieves 99% accuracy, precision, recall, and F1 scores on the otolith dataset collected by the Marine Science Research Institute of Shandong Province, exhibiting superior feature extraction capabilities compared with other mainstream baselines and effectively capturing the fine-grained texture information of otoliths. Moreover, visualization analyses further validate the model’s ability to attend to key discriminative regions. This work offers an efficient and reliable technical solution for the intelligent identification and management of fishery resources, strongly promoting the digitalization and smart development of fisheries. Biological sciences/Ecology Earth and environmental sciences/Ecology Physical sciences/Mathematics and computing Earth and environmental sciences/Ocean sciences Fish species identification Otolith recognition Image processing Data augmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 11 Mar, 2026 Editor invited by journal 24 Nov, 2025 Editor assigned by journal 17 Nov, 2025 Submission checks completed at journal 17 Nov, 2025 First submitted to journal 13 Nov, 2025 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-8109572","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":604689613,"identity":"2da6b816-bf77-48ec-851b-0a558ffc868c","order_by":0,"name":"XIAO GU","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIie3RuwrCMBSA4VMK6XJq15SKvkJAqAiiryIUnDI4OtalLnXXwYdw69hS0CUP4Nguuijo6GaNFxCxdXTIP4WQj9wAVKo/jBkTPz4xisTwn3ODCoJpks/H3XoN418JHXotFMNug75WVpA2cNdeBCkSe5/pZtQDy+AMLtF30vGFS8834nCmm8IDOzwwbSZKDpaEj10cDroZxMC2hdWCEpKi65jyYJtMkn4lWRN5fSQU2H0XWkE6oS4fGQlyliyFh1TsRsmshLSbufzKfnO6ybNj1GtYU2+VXUrIW7HmA8rBj6CoICqVSqX66Armx08Pl5IONwAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong Academy of Social Sciences","correspondingAuthor":true,"prefix":"","firstName":"XIAO","middleName":"","lastName":"GU","suffix":""},{"id":604689614,"identity":"49eaeefb-9aec-4f1e-bb64-436907f6233b","order_by":1,"name":"Aihuan Song","email":"","orcid":"","institution":"Marine Science Research Institute of Shandong Province","correspondingAuthor":false,"prefix":"","firstName":"Aihuan","middleName":"","lastName":"Song","suffix":""},{"id":604689615,"identity":"1c60835e-0e70-46fd-bc4c-a06af54aaef0","order_by":2,"name":"Yingjun Wang","email":"","orcid":"","institution":"Marine Science Research Institute of Shandong Province","correspondingAuthor":false,"prefix":"","firstName":"Yingjun","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-11-14 01:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8109572/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8109572/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104780808,"identity":"2551eefe-9625-4741-aa20-b83f28eca242","added_by":"auto","created_at":"2026-03-17 07:54:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1187422,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8109572/v1_covered_284c9893-1373-4685-8d37-85b3a404502b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eResearch on Fish Otolith Image Recognition Enhanced by EfficientNet\u003c/p\u003e","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Fish species identification, Otolith recognition, Image processing, Data augmentation","lastPublishedDoi":"10.21203/rs.3.rs-8109572/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8109572/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Fish otolith identification is of great significance for the species recognition and scientific management of fishery resources. Traditional methods for otolith identification are highly dependent on expert experience, and the process is cumbersome and subjective. In addition, factors such as limited sample sizes and the subtle, difficult-to-distinguish features of otoliths lead to unsatisfactory identification performance. To this end, this paper proposes a lightweight EfficientNet-based framework that integrates data augmentation and texture feature optimization for otolith image classification. This approach significantly reduces model parameters and computational cost while maintaining classification accuracy. Experimental results demonstrate that the proposed model achieves 99\\% accuracy, precision, recall, and F1 scores on the otolith dataset collected by the Marine Science Research Institute of Shandong Province, exhibiting superior feature extraction capabilities compared with other mainstream baselines and effectively capturing the fine-grained texture information of otoliths. Moreover, visualization analyses further validate the model’s ability to attend to key discriminative regions. This work offers an efficient and reliable technical solution for the intelligent identification and management of fishery resources, strongly promoting the digitalization and smart development of fisheries. ","manuscriptTitle":"Research on Fish Otolith Image Recognition Enhanced by EfficientNet","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-13 03:33:47","doi":"10.21203/rs.3.rs-8109572/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-03-11T12:45:18+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-24T11:33:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-17T13:54:40+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-17T13:54:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-11-14T01:13:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3591ecc3-75a1-455f-9690-0669dd6d92b6","owner":[],"postedDate":"March 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64429071,"name":"Biological sciences/Ecology"},{"id":64429072,"name":"Earth and environmental sciences/Ecology"},{"id":64429073,"name":"Physical sciences/Mathematics and computing"},{"id":64429074,"name":"Earth and environmental sciences/Ocean sciences"}],"tags":[],"updatedAt":"2026-03-13T03:33:47+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-13 03:33:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8109572","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8109572","identity":"rs-8109572","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}