Fast and Accurate Meat Freshness Classification Using Depthwise Separable Convolution and SPPF

Fast and Accurate Meat Freshness Classification Using Depthwise Separable Convolution and SPPF | 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 Fast and Accurate Meat Freshness Classification Using Depthwise Separable Convolution and SPPF Khanh-Duy Cao-Phan, Hoang-Khang Dang, Huyen-Tran Tran-Quynh, Minh-Phuc Lam-Doan, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8630971/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Ensuring the freshness of meat is vital for food safety, consumer trust, and waste reduction. Traditional chemical and microbiological tests, though reliable, are destructive and time-consuming, limiting their suitability for real-time monitoring. This study introduces DW–SPPFNet, a lightweight deep learning framework designed for rapid, non-destructive classification of meat freshness from RGB images. The model integrates Depthwise Separable Convolution (DW) to minimize redundant computation and Spatial Pyramid Pooling Feature-lite (SPPF-lite) to enhance multi-scale spatial representation. This combination achieves a superior trade-off between accuracy and efficiency, enabling edge-level deployment. Trained and tested on a dataset of 10,372 labeled pork images, DW–SPPFNet achieved 98.31% test accuracy, 98.32% macro-F1, and a Cohen’s $\kappa$ of 0.9747, surpassing state-of-the-art lightweight backbones such as MobileNetV4-S and EfficientViT. The model operates at 2.72 ms per image with a minimal computational footprint (0.213 GFLOPs, 1.63M parameters), allowing real-time inference on resource-limited devices. Meat freshness classification Meat freshness assessment Edge AI for food safety Non-destructive food quality assessment Depthwise separable convolution SPPF (Spatial Pyramid Pooling–Fast) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Feb, 2026 Reviews received at journal 09 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviewers agreed at journal 03 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviewers agreed at journal 29 Jan, 2026 Reviewers invited by journal 29 Jan, 2026 Editor assigned by journal 23 Jan, 2026 Submission checks completed at journal 23 Jan, 2026 First submitted to journal 18 Jan, 2026 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-8630971","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":582865344,"identity":"5a75f8c4-f337-43cc-a981-70c213bdd650","order_by":0,"name":"Khanh-Duy Cao-Phan","email":"","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":false,"prefix":"","firstName":"Khanh-Duy","middleName":"","lastName":"Cao-Phan","suffix":""},{"id":582865345,"identity":"d7cccfda-1b9a-4cb5-963c-0cdedab09a13","order_by":1,"name":"Hoang-Khang Dang","email":"","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":false,"prefix":"","firstName":"Hoang-Khang","middleName":"","lastName":"Dang","suffix":""},{"id":582865346,"identity":"66937ae8-814c-48de-b324-904c9a0ec823","order_by":2,"name":"Huyen-Tran Tran-Quynh","email":"","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":false,"prefix":"","firstName":"Huyen-Tran","middleName":"","lastName":"Tran-Quynh","suffix":""},{"id":582865347,"identity":"ebc6e893-807e-479c-81b6-1691d7e974a8","order_by":3,"name":"Minh-Phuc Lam-Doan","email":"","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":false,"prefix":"","firstName":"Minh-Phuc","middleName":"","lastName":"Lam-Doan","suffix":""},{"id":582865348,"identity":"1b351f76-575c-4a73-a3c3-ff9042c0a163","order_by":4,"name":"Huyen-Trang Luu","email":"","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":false,"prefix":"","firstName":"Huyen-Trang","middleName":"","lastName":"Luu","suffix":""},{"id":582865350,"identity":"95c09082-6fcb-4398-92a9-e2c56bbe0121","order_by":5,"name":"Hong-Quan Bui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYBACAwbGNhib8UECwwEgnUC8FmYDIrUwsMHYbBIMxGgxl0hue/BxR63shuNnj1U8bLvDwM+eY8DMuwO3FssZie2GM88cN95wJi/tRmLbMwbJnjdALWfwOAyoTJq37VjihgM5ZkD2YaBIjgHjzDZitJx/Y1YA0mJPpJaaxA03cswYwLZI5BgwfMSjxbLnYZvkzLYDxjNvvDGWSDh3mEfizLOCA/i0mLOnP5P42FYn23c+x/Djj7LDcvztyRsfJOLRAgWHGRugLB4QcYCgBgaGOriWUTAKRsEoGAUYAABOJFtfm/HZLAAAAABJRU5ErkJggg==","orcid":"","institution":"Industrial University of Ho Chi Minh City","correspondingAuthor":true,"prefix":"","firstName":"Hong-Quan","middleName":"","lastName":"Bui","suffix":""}],"badges":[],"createdAt":"2026-01-18 11:38:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8630971/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8630971/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101752619,"identity":"3e779bea-eb8e-4a53-97ff-7483635b8409","added_by":"auto","created_at":"2026-02-03 10:28:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":473835,"visible":true,"origin":"","legend":"","description":"","filename":"FastandAccurateMeatFreshnessClassificationUsing.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8630971/v1_covered_2a2d2afb-13c4-4597-9344-a9b8e94f3751.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fast and Accurate Meat Freshness Classification Using Depthwise Separable Convolution and SPPF","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":"food-analytical-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Food Analytical Methods](https://www.springer.com/journal/12161)","snPcode":"12161","submissionUrl":"https://submission.nature.com/new-submission/12161/3","title":"Food Analytical Methods","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Meat freshness classification, Meat freshness assessment, Edge AI for food safety, Non-destructive food quality assessment, Depthwise separable convolution, SPPF (Spatial Pyramid Pooling–Fast)","lastPublishedDoi":"10.21203/rs.3.rs-8630971/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8630971/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\nEnsuring the freshness of meat is vital for food safety, consumer trust, and waste reduction. Traditional chemical and microbiological tests, though reliable, are destructive and time-consuming, limiting their suitability for real-time monitoring. This study introduces DW–SPPFNet, a lightweight deep learning framework designed for rapid, non-destructive classification of meat freshness from RGB images. The model integrates Depthwise Separable Convolution (DW) to minimize redundant computation and Spatial Pyramid Pooling Feature-lite (SPPF-lite) to enhance multi-scale spatial representation. This combination achieves a superior trade-off between accuracy and efficiency, enabling edge-level deployment. Trained and tested on a dataset of 10,372 labeled pork images, DW–SPPFNet achieved 98.31\\% test accuracy, 98.32\\% macro-F1, and a Cohen’s $\\kappa$ of 0.9747, surpassing state-of-the-art lightweight backbones such as MobileNetV4-S and EfficientViT. The model operates at 2.72 ms per image with a minimal computational footprint (0.213 GFLOPs, 1.63M parameters), allowing real-time inference on resource-limited devices. \n\n","manuscriptTitle":"Fast and Accurate Meat Freshness Classification Using Depthwise Separable Convolution and SPPF","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-01 13:54:45","doi":"10.21203/rs.3.rs-8630971/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-15T11:13:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-09T07:21:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-04T04:35:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324282953271666330320478638633033408390","date":"2026-02-04T04:21:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-03T07:30:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"130173798269861087465911414904697422409","date":"2026-01-30T07:02:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43525481261741689899177215260575585529","date":"2026-01-29T09:33:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-29T09:12:39+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-23T08:42:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-23T08:36:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Food Analytical Methods","date":"2026-01-18T11:28:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"food-analytical-methods","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Food Analytical Methods](https://www.springer.com/journal/12161)","snPcode":"12161","submissionUrl":"https://submission.nature.com/new-submission/12161/3","title":"Food Analytical Methods","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d5d08526-4ea7-49b8-a6db-ef25cf19bd8a","owner":[],"postedDate":"February 1st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-26T09:11:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-01 13:54:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8630971","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8630971","identity":"rs-8630971","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}