Segment Anything Model for Industrial Vision: A Comprehensive Evaluation with a New Metric, a New Dataset, and a Toolbox

Segment Anything Model for Industrial Vision: A Comprehensive Evaluation with a New Metric, a New Dataset, and a Toolbox | 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 Segment Anything Model for Industrial Vision: A Comprehensive Evaluation with a New Metric, a New Dataset, and a Toolbox Xiaopin Zhong, Chongxin Hu, Jiayuan Xie, Jianye Yi, You Zhou, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4257722/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Image segmentation is a fundamental task of computer vision, and plays a vital role in intelligent manufacturing for detection of surface defects. Recent emergence of segmentation foundation models, such as segment anything model (SAM), provide remarkable versatility and performance across various segmentation tasks with natural images. For industrial vision, defect image segmentation poses a significant challenge due to limited sample sizes, vast scene variations, and diverse defect shapes, etc. There are three issues on evaluating SAM's performance on industrial images: existing public defect datasets are too simple and small, and the performance metrics tend to saturate; are the existing metrics objective for such special defect images? And how to evaluate SAM easily? Therefore, this study aims to comprehensively evaluate SAM's performance on industrial images. Firstly, we release a large dataset of mobile phone screen for enhancing data diversity. Secondly, a new evaluation metric is proposed for fitting in the industrial defects. And lastly, an open toolkit is available for easily transferred to other defect images. We also identify the potential paths for future research, and believe that our contribution is beneficial for the implementation of vision foundation models, such as SAM, in both academic and industrial communities. Physical sciences/Engineering Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-4257722","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":292668986,"identity":"7fb901af-a995-4f44-9878-0e8e72109487","order_by":0,"name":"Xiaopin Zhong","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Xiaopin","middleName":"","lastName":"Zhong","suffix":""},{"id":292668987,"identity":"78ec3da6-a706-46aa-baa5-5c788b58ab6a","order_by":1,"name":"Chongxin Hu","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Chongxin","middleName":"","lastName":"Hu","suffix":""},{"id":292668988,"identity":"8b948a25-9d68-41db-afdf-002f3e31476c","order_by":2,"name":"Jiayuan Xie","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Jiayuan","middleName":"","lastName":"Xie","suffix":""},{"id":292668989,"identity":"6b72c48d-f2e7-4f30-b3d2-450de42f6b24","order_by":3,"name":"Jianye Yi","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Jianye","middleName":"","lastName":"Yi","suffix":""},{"id":292668990,"identity":"2ee66980-e25c-4ff6-9c3a-51363de49e22","order_by":4,"name":"You Zhou","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"You","middleName":"","lastName":"Zhou","suffix":""},{"id":292668991,"identity":"a1f184eb-1fd8-4541-ac6a-73e5c2efa5c9","order_by":5,"name":"Deyu Zeng","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Deyu","middleName":"","lastName":"Zeng","suffix":""},{"id":292668992,"identity":"6db947b2-8a0e-4675-b796-e1088ea183f5","order_by":6,"name":"Lei Zhou","email":"","orcid":"","institution":"Guangdong Laboratory of Artificial Intelligence and Digital Economy","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Zhou","suffix":""},{"id":292668993,"identity":"4b7c66a4-c402-44e8-8a2f-11691fc8cd81","order_by":7,"name":"Kun Chen","email":"","orcid":"","institution":"Guangdong Laboratory of Artificial Intelligence and Digital Economy","correspondingAuthor":false,"prefix":"","firstName":"Kun","middleName":"","lastName":"Chen","suffix":""},{"id":292668994,"identity":"dc427dd7-8b08-42e2-a6ab-75ca1c313b3e","order_by":8,"name":"Weixiang Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYFAC5oYDDBUQpgSRWhiBWs6QqoWBsY0ULQY3EhsP886rszc4wHzwNg+DXR5hLWcONhzm3XaY2eAAW7I1D0NyMUEtZscbQVoOsBkc4DGT5mE4kNhAUMthRqCWOXU8Bgf4vxGpBWxLA7ME0BY24rTYA/1ycM6xwwaSh9mMLecYJBPWIjkj+fCHNzV19nzHmx/eeFNhR1gLAjCDCAPi1Y+CUTAKRsEowAMAOGw7i21IRv4AAAAASUVORK5CYII=","orcid":"","institution":"Shenzhen University","correspondingAuthor":true,"prefix":"","firstName":"Weixiang","middleName":"","lastName":"Liu","suffix":""},{"id":292668995,"identity":"3651270b-730b-4943-a83e-b85f1980fd9c","order_by":9,"name":"Zongze Wu","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Zongze","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2024-04-12 12:20:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4257722/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4257722/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68152265,"identity":"f132dce5-9680-420e-9183-4d15763b0a64","added_by":"auto","created_at":"2024-11-04 07:17:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3410503,"visible":true,"origin":"","legend":"","description":"","filename":"SegmentAnythingModelforIndustrialVisionAComprehensiveEvaluationwithaNewMetricaNewDatasetandaToolbox.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4257722/v1_covered_78314e18-2c18-4b1c-82ac-83394c34009b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Segment Anything Model for Industrial Vision: A Comprehensive Evaluation with a New Metric, a New Dataset, and a Toolbox","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4257722/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4257722/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Image segmentation is a fundamental task of computer vision, and plays a vital role in intelligent manufacturing for detection of surface defects. Recent emergence of segmentation foundation models, such as segment anything model (SAM), provide remarkable versatility and performance across various segmentation tasks with natural images. For industrial vision, defect image segmentation poses a significant challenge due to limited sample sizes, vast scene variations, and diverse defect shapes, etc. There are three issues on evaluating SAM's performance on industrial images: existing public defect datasets are too simple and small, and the performance metrics tend to saturate; are the existing metrics objective for such special defect images? And how to evaluate SAM easily? Therefore, this study aims to comprehensively evaluate SAM's performance on industrial images. Firstly, we release a large dataset of mobile phone screen for enhancing data diversity. Secondly, a new evaluation metric is proposed for fitting in the industrial defects. And lastly, an open toolkit is available for easily transferred to other defect images. We also identify the potential paths for future research, and believe that our contribution is beneficial for the implementation of vision foundation models, such as SAM, in both academic and industrial communities.","manuscriptTitle":"Segment Anything Model for Industrial Vision: A Comprehensive Evaluation with a New Metric, a New Dataset, and a Toolbox","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-19 02:37:50","doi":"10.21203/rs.3.rs-4257722/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":"ce2a5648-86a0-4927-b38c-6f1e06c8b4f4","owner":[],"postedDate":"April 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":30835043,"name":"Physical sciences/Engineering"},{"id":30835044,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-11-04T07:08:54+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-19 02:37:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4257722","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4257722","identity":"rs-4257722","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}