Industrial Damage Sample Image Generation Method Based on Improved DCGAN

Industrial Damage Sample Image Generation Method Based on Improved DCGAN | 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 Industrial Damage Sample Image Generation Method Based on Improved DCGAN Hongfei Li, Xudong Wang, Wengang Ao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6155138/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Jul, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 11 You are reading this latest preprint version Abstract To address the limited availability of atmospheric natural environment test samples and the challenge of obtaining sufficient industrial damage sample data for deep learning, we propose IDS-GAN, a novel data generation method based on an improved DCGAN for small-sample industrial damage modeling. First, a Wasserstein distance loss function with a gradient penalty term is introduced as an adversarial loss to mitigate mode collapse and stabilize training. Furthermore, L1 loss and Structural Similarity Index Measure (SSIM) loss are incorporated to guide the generator’s training. Residual blocks are added to the generator to address the gradient vanishing problem commonly encountered in deep networks during high-resolution image generation. Experimental results demonstrate that, compared to a progressively trained DCGAN, the proposed IDS-GAN model generates industrial damage sample images with significantly higher quality and more distinct features. Specifically, the Fréchet Inception Distance (FID) score decreased by 18.6%, while the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) improved by 5.1% and 21.1%, respectively. These results indicate that IDS-GAN is an effective approach for generating industrial damage sample datasets, offering potential applications in relevant research fields. Generative Adversarial Network Data Augmentation Industrial Damage Images Sample Convolutional Neural Network Image Generation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 04 Jul, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 24 Apr, 2025 Reviews received at journal 24 Apr, 2025 Reviews received at journal 13 Apr, 2025 Reviewers agreed at journal 13 Apr, 2025 Reviewers agreed at journal 13 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers invited by journal 12 Apr, 2025 Submission checks completed at journal 05 Apr, 2025 First submitted to journal 05 Apr, 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-6155138","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":447610469,"identity":"7b3cbda3-68fb-4a82-b4a9-ba29e922142c","order_by":0,"name":"Hongfei Li","email":"","orcid":"","institution":"Chongqing Technology and Business University","correspondingAuthor":false,"prefix":"","firstName":"Hongfei","middleName":"","lastName":"Li","suffix":""},{"id":447610470,"identity":"15ddfe9a-e390-472c-af5e-b199d234dfee","order_by":1,"name":"Xudong Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYPACZhA+wMDYAOIkEK2FLYHhIIlaeAyI02Jw/Ozh17xt1nLm/Gs+fv644zADP3uOAcPPHXi0nMlLs5zZlm5sOePtZomDZw4zSPa8MWDsPYNbi9mBHDODj22HEzfcOLuN4WDbYQaDGzkGzIxteLScf2NmkAjWcuYZWIs9QS03cowfgG0538MGsUWCgBb7G2/MGGecSzc2uMFmLHH2TDqPxJlnBQd78WiR7M8x/sxTZi1ncP7www+VO6zl+NuTNz74iUcLELBJgCmJBDDFAyIO4NUAjMYPYIqfkLpRMApGwSgYsQAAT8NakcwNNQ0AAAAASUVORK5CYII=","orcid":"","institution":"Chongqing Technology and Business University","correspondingAuthor":true,"prefix":"","firstName":"Xudong","middleName":"","lastName":"Wang","suffix":""},{"id":447610471,"identity":"9847fe59-19ad-4591-bdd4-1ce5c7e24d55","order_by":2,"name":"Wengang Ao","email":"","orcid":"","institution":"National Research Base of Intelligent Manufacturing Service","correspondingAuthor":false,"prefix":"","firstName":"Wengang","middleName":"","lastName":"Ao","suffix":""}],"badges":[],"createdAt":"2025-03-04 13:53:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6155138/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6155138/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04460-6","type":"published","date":"2025-07-04T15:57:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":86179072,"identity":"df4bdb23-0b7e-48b3-b795-8391fb0b16c6","added_by":"auto","created_at":"2025-07-07 16:15:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1064633,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6155138/v1_covered_6202293e-3740-4d1a-a3e2-493ca868db11.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Industrial Damage Sample Image Generation Method Based on Improved DCGAN","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Generative Adversarial Network, Data Augmentation, Industrial Damage Images Sample, Convolutional Neural Network, Image Generation","lastPublishedDoi":"10.21203/rs.3.rs-6155138/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6155138/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the limited availability of atmospheric natural environment test samples and the challenge of obtaining sufficient industrial damage sample data for deep learning, we propose IDS-GAN, a novel data generation method based on an improved DCGAN for small-sample industrial damage modeling. First, a Wasserstein distance loss function with a gradient penalty term is introduced as an adversarial loss to mitigate mode collapse and stabilize training. Furthermore, L1 loss and Structural Similarity Index Measure (SSIM) loss are incorporated to guide the generator\u0026rsquo;s training. Residual blocks are added to the generator to address the gradient vanishing problem commonly encountered in deep networks during high-resolution image generation. Experimental results demonstrate that, compared to a progressively trained DCGAN, the proposed IDS-GAN model generates industrial damage sample images with significantly higher quality and more distinct features. Specifically, the Fr\u0026eacute;chet Inception Distance (FID) score decreased by 18.6%, while the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) improved by 5.1% and 21.1%, respectively. These results indicate that IDS-GAN is an effective approach for generating industrial damage sample datasets, offering potential applications in relevant research fields.\u003c/p\u003e","manuscriptTitle":"Industrial Damage Sample Image Generation Method Based on Improved DCGAN","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-29 10:59:23","doi":"10.21203/rs.3.rs-6155138/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-24T17:02:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-24T12:40:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-14T02:55:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"28605420818437626972732328852459326638","date":"2025-04-13T21:16:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"83106641486217331566959546056890472155","date":"2025-04-13T06:23:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254603901798658864856012622479290648716","date":"2025-04-13T03:26:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11580086258042682542769284181776539705","date":"2025-04-13T02:47:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301588975703240613518665488805618370193","date":"2025-04-13T02:42:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-13T02:40:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-05T14:16:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-04-05T14:09:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a91333b1-861e-40b5-9d2d-15668ac26d0c","owner":[],"postedDate":"April 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-07T16:04:17+00:00","versionOfRecord":{"articleIdentity":"rs-6155138","link":"https://doi.org/10.1007/s11760-025-04460-6","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-07-04 15:57:52","publishedOnDateReadable":"July 4th, 2025"},"versionCreatedAt":"2025-04-29 10:59:23","video":"","vorDoi":"10.1007/s11760-025-04460-6","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04460-6","workflowStages":[]},"version":"v1","identity":"rs-6155138","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6155138","identity":"rs-6155138","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}