Visual Quality Assessment of E-Commerce Product Images Using Convolutional Neural Networks

Visual Quality Assessment of E-Commerce Product Images Using Convolutional Neural Networks | 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 Visual Quality Assessment of E-Commerce Product Images Using Convolutional Neural Networks Imad Tbaileh, Selami Bagriyanik This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6584522/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted 12 You are reading this latest preprint version Abstract Purpose: High-quality product images are vital in shaping consumer trust and driving engagement on e-commerce platforms. This study proposes a deep learning-based approach for evaluating the visual quality of product images, with the aim of improving the overall customer experience and presentation standards in online marketplaces. Methods: A custom-labeled dataset was developed, containing thousands of product images categorized into five quality levels. A convolutional neural network (CNN) was trained to classify these images based on their visual quality. In addition, two well-known architectures, MobileNetV2 and EfficientNetB0, were trained under identical conditions to serve as benchmarks for performance comparison. Results: The proposed CNN model achieved an accuracy of 94.93%, outperform-ing both MobileNetV2 (76.60%) and EfficientNetB0 (92.77%). It also delivered the highest performance in terms of precision, recall, and F1-score, confirming its effectiveness in this domain. Conclusion: The results highlight the CNN model’s suitability for real-time quality assessment of e-commerce images. Its strong performance and efficiency make it a promising candidate for integration into commercial platforms. Future work will investigate the use of transformer-based models and more diverse training data to further improve accuracy and generalizability. Computer vision Deep learning Product image quality assessment E-commerce Customer experience Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 10 Oct, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 17 Jul, 2025 Reviews received at journal 03 Jul, 2025 Reviews received at journal 30 Jun, 2025 Reviewers agreed at journal 24 Jun, 2025 Reviewers agreed at journal 24 Jun, 2025 Reviewers agreed at journal 24 Jun, 2025 Reviewers agreed at journal 23 Jun, 2025 Reviewers agreed at journal 23 Jun, 2025 Reviewers invited by journal 23 Jun, 2025 Editor assigned by journal 15 Jun, 2025 Submission checks completed at journal 12 May, 2025 First submitted to journal 03 May, 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-6584522","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":475696489,"identity":"a62fe7c9-49b8-4a49-92bd-ee0bc18b796a","order_by":0,"name":"Imad Tbaileh","email":"data:image/png;base64,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","orcid":"","institution":"Bahçeşehir University","correspondingAuthor":true,"prefix":"","firstName":"Imad","middleName":"","lastName":"Tbaileh","suffix":""},{"id":475696491,"identity":"697cc0fa-fe99-4a86-9447-bd7cdf3a4a07","order_by":1,"name":"Selami Bagriyanik","email":"","orcid":"","institution":"Bahçeşehir University","correspondingAuthor":false,"prefix":"","firstName":"Selami","middleName":"","lastName":"Bagriyanik","suffix":""}],"badges":[],"createdAt":"2025-05-03 14:08:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6584522/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6584522/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00530-025-02009-8","type":"published","date":"2025-10-10T15:58:25+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93419926,"identity":"2455a419-4d39-4089-8965-c2ca10bd04a0","added_by":"auto","created_at":"2025-10-13 16:08:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":881080,"visible":true,"origin":"","legend":"","description":"","filename":"snarticlen.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6584522/v1_covered_562b7a62-dc0d-46d1-aca8-8ebbc70cf95f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Visual Quality Assessment of E-Commerce Product Images Using Convolutional Neural Networks","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":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Computer vision, Deep learning, Product image quality assessment, E-commerce, Customer experience","lastPublishedDoi":"10.21203/rs.3.rs-6584522/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6584522/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePurpose: High-quality product images are vital in shaping consumer trust and driving engagement on e-commerce platforms. This study proposes a deep learning-based approach for evaluating the visual quality of product images, with the aim of improving the overall customer experience and presentation standards in online marketplaces.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: A custom-labeled dataset was developed, containing thousands of product images categorized into five quality levels. A convolutional neural network (CNN) was trained to classify these images based on their visual quality. In addition, two well-known architectures, MobileNetV2 and EfficientNetB0, were trained under identical conditions to serve as benchmarks for performance comparison.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: The proposed CNN model achieved an accuracy of 94.93%, outperform-ing both MobileNetV2 (76.60%) and EfficientNetB0 (92.77%). It also delivered the highest performance in terms of precision, recall, and F1-score, confirming its effectiveness in this domain.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: The results highlight the CNN model’s suitability for real-time quality assessment of e-commerce images. Its strong performance and efficiency make it a promising candidate for integration into commercial platforms. Future work will investigate the use of transformer-based models and more diverse training data to further improve accuracy and generalizability.\u003c/p\u003e","manuscriptTitle":"Visual Quality Assessment of E-Commerce Product Images Using Convolutional Neural Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-25 06:36:20","doi":"10.21203/rs.3.rs-6584522/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-17T11:11:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-04T03:42:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-30T12:28:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73961664631957971213618095959499872015","date":"2025-06-24T10:30:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306351606877405263381867644829167398383","date":"2025-06-24T10:30:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"261175167622465417119620422105685832370","date":"2025-06-24T04:30:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271697979718642449825990777180960674523","date":"2025-06-24T01:10:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"312190065868141760139775473455451295863","date":"2025-06-23T12:30:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-23T11:57:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-16T02:47:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-12T09:04:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Multimedia Systems","date":"2025-05-03T14:04:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"multimedia-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mmsj","sideBox":"Learn more about [Multimedia Systems](http://link.springer.com/journal/530)","snPcode":"530","submissionUrl":"https://submission.nature.com/new-submission/530/3","title":"Multimedia Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"22c25f66-aec7-486d-a100-418156408e44","owner":[],"postedDate":"June 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-13T16:05:40+00:00","versionOfRecord":{"articleIdentity":"rs-6584522","link":"https://doi.org/10.1007/s00530-025-02009-8","journal":{"identity":"multimedia-systems","isVorOnly":false,"title":"Multimedia Systems"},"publishedOn":"2025-10-10 15:58:25","publishedOnDateReadable":"October 10th, 2025"},"versionCreatedAt":"2025-06-25 06:36:20","video":"","vorDoi":"10.1007/s00530-025-02009-8","vorDoiUrl":"https://doi.org/10.1007/s00530-025-02009-8","workflowStages":[]},"version":"v1","identity":"rs-6584522","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6584522","identity":"rs-6584522","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}