Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16

Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16 | 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 Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16 Subhrangshu Adhikary, Saikat Banerjee, Rajani Singh, Ashutosh Dhar Dwivedi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2266266/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract An intelligent detection and recognition model for the fish species from camera footage is urgently required as fishery contributes to a large portion of the world economy, and these kinds of advanced models can aid fishermen on a large scale. Such models incorporating a pick-and-place machine can be beneficial to sorting different fish species in bulk without human intervention, significantly reducing costs for large-scale fishing industries. Existing methods for detecting and recognizing fish species have many limitations, such as limited scalability, detection accuracy, failure to detect multiple species, degraded performance at a lower resolution, or pinpointing the exact location of the fish. Modifying the head of a compelling deep learning model, namely VGG-16, with pre-trained weights, can be used to detect both the species of the fish and find the exact location of the fish in an image by implementing a modified YOLO to incorporate the bounding box regression head. We have proposed using the ESRGAN algorithm and the proposed neural network to amplify the image resolution by a factor of 4. With this method, an overall detection accuracy of 96.5% has been obtained. The experiment has been conducted based on a total of 9460 images spread across 9 species. After further improving the model, a pick-and-place machine could be integrated to quickly sort the fish according to their species in different large-scale fish industries. VGG-16 ESRGAN Fish Species Recognition Classification Object Detection Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-2266266","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":152211138,"identity":"52f77adf-8c3a-4e62-9e62-b125e818cf78","order_by":0,"name":"Subhrangshu Adhikary","email":"data:image/png;base64,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","orcid":"","institution":"Spiraldevs Automation Industries Pvt. Ltd","correspondingAuthor":true,"prefix":"","firstName":"Subhrangshu","middleName":"","lastName":"Adhikary","suffix":""},{"id":298490512,"identity":"d224b4a0-8a41-43d3-9be2-baac5997e7cc","order_by":1,"name":"Saikat Banerjee","email":"","orcid":"","institution":"Aerosys Defence and Aerospace Pvt. Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Saikat","middleName":"","lastName":"Banerjee","suffix":""},{"id":298490513,"identity":"e4cb5269-598d-402e-9669-d4e4e65abe36","order_by":2,"name":"Rajani Singh","email":"","orcid":"","institution":"Copenhagen Business School","correspondingAuthor":false,"prefix":"","firstName":"Rajani","middleName":"","lastName":"Singh","suffix":""},{"id":298490514,"identity":"421ff24d-e04f-4525-ae45-c8d176d894db","order_by":3,"name":"Ashutosh Dhar Dwivedi","email":"","orcid":"","institution":"Aalborg University","correspondingAuthor":false,"prefix":"","firstName":"Ashutosh","middleName":"Dhar","lastName":"Dwivedi","suffix":""}],"badges":[],"createdAt":"2022-11-12 13:29:17","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-2266266/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-2266266/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55822415,"identity":"db31b850-ac0d-4350-9b31-31a317f91dfb","added_by":"auto","created_at":"2024-05-04 00:10:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":734356,"visible":true,"origin":"","legend":"","description":"","filename":"Fishspeciesdeeplearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2266266/v2_covered_e0af434c-8b30-468c-8bbf-7e7d71dfaf92.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16","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":"VGG-16, ESRGAN, Fish Species Recognition, Classification, Object Detection","lastPublishedDoi":"10.21203/rs.3.rs-2266266/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2266266/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAn intelligent detection and recognition model for the fish species from camera footage is urgently required\u003c/p\u003e\n\u003cp\u003eas fishery contributes to a large portion of the world economy, and these kinds of advanced models can\u003c/p\u003e\n\u003cp\u003eaid fishermen on a large scale. Such models incorporating a pick-and-place machine can be beneficial to\u003c/p\u003e\n\u003cp\u003esorting different fish species in bulk without human intervention, significantly reducing costs for large-scale\u003c/p\u003e\n\u003cp\u003efishing industries. Existing methods for detecting and recognizing fish species have many limitations,\u003c/p\u003e\n\u003cp\u003esuch as limited scalability, detection accuracy, failure to detect multiple species, degraded performance at\u003c/p\u003e\n\u003cp\u003ea lower resolution, or pinpointing the exact location of the fish. Modifying the head of a compelling deep\u003c/p\u003e\n\u003cp\u003elearning model, namely VGG-16, with pre-trained weights, can be used to detect both the species of the\u003c/p\u003e\n\u003cp\u003efish and find the exact location of the fish in an image by implementing a modified YOLO to incorporate\u003c/p\u003e\n\u003cp\u003ethe bounding box regression head. We have proposed using the ESRGAN algorithm and the proposed\u003c/p\u003e\n\u003cp\u003eneural network to amplify the image resolution by a factor of 4. With this method, an overall detection\u003c/p\u003e\n\u003cp\u003eaccuracy of 96.5% has been obtained. The experiment has been conducted based on a total of 9460\u003c/p\u003e\n\u003cp\u003eimages spread across 9 species. After further improving the model, a pick-and-place machine could be\u003c/p\u003e\n\u003cp\u003eintegrated to quickly sort the fish according to their species in different large-scale fish industries.\u003c/p\u003e","manuscriptTitle":"Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2024-05-03 23:54:00","doi":"10.21203/rs.3.rs-2266266/v2","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}},{"code":1,"date":"2022-11-15 08:38:25","doi":"10.21203/rs.3.rs-2266266/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":"59fe712f-7a7c-46b1-b164-ce84e86711d2","owner":[],"postedDate":"May 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2023-04-05T02:59:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-03 23:54:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-2266266","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2266266","identity":"rs-2266266","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}