{"paper_id":"424b7ac2-5fd5-4c4e-9ba3-54f22ac775c3","body_text":"Food Image Segmentation based on Deep and Shallow Dual-branch Network | 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 Food Image Segmentation based on Deep and Shallow Dual-branch Network Zhiyong Xiao, Yang Li, Zhaohong Deng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4879002/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Jan, 2025 Read the published version in Multimedia Systems → Version 1 posted 10 You are reading this latest preprint version Abstract Food image segmentation is an important research area within the fields of computer vision and machine learning. Traditional methods often input high-resolution food images at large sizes directly into network models, which leads to high computational costs. Additionally, effectively distinguishing between different foods with similar appearances and the same food in different forms poses a significant challenge. This paper introduces a dual-branch structure network based on Swin Transformer and convolutional neural networks (FDSNet), which significantly reduces the computational costs of processing large-size input images. Furthermore, this study introduces a multi-scale feature fusion technique that effectively integrates feature information from different scales and levels, enabling the model to more accurately segment and recognize different foods. Our method can more precisely perform food image segmentation, helping people improve their diets and manage health better. Training and testing on the FoodSeg103 and UECFoodPixComplete public food datasets have shown that our model achieves mean Intersection over Union (IoU) scores of 47.34 and 75.89, respectively, demonstrating higher accuracy and computational efficiency compared to other methods. Food image segmentation Deep learning Swin Transformer Food health Multi-scale feature fusion Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 29 Jan, 2025 Read the published version in Multimedia Systems → Version 1 posted Editorial decision: Revision requested 05 Nov, 2024 Reviews received at journal 17 Oct, 2024 Reviewers agreed at journal 09 Oct, 2024 Reviews received at journal 23 Sep, 2024 Reviewers agreed at journal 22 Sep, 2024 Reviewers agreed at journal 16 Sep, 2024 Reviewers invited by journal 11 Sep, 2024 Editor assigned by journal 05 Sep, 2024 Submission checks completed at journal 09 Aug, 2024 First submitted to journal 08 Aug, 2024 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-4879002\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":358192015,\"identity\":\"d79272e0-40b6-43b0-a736-96bd9367ff78\",\"order_by\":0,\"name\":\"Zhiyong Xiao\",\"email\":\"data:image/png;base64,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\",\"orcid\":\"\",\"institution\":\"Jiangnan University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Zhiyong\",\"middleName\":\"\",\"lastName\":\"Xiao\",\"suffix\":\"\"},{\"id\":358192016,\"identity\":\"5e21d0a4-b5a7-48a9-b8f4-8d4b22035366\",\"order_by\":1,\"name\":\"Yang Li\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Jiangnan University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Yang\",\"middleName\":\"\",\"lastName\":\"Li\",\"suffix\":\"\"},{\"id\":358192017,\"identity\":\"9bcf2ecc-de5e-47db-b1bf-73751b8f2bea\",\"order_by\":2,\"name\":\"Zhaohong Deng\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Jiangnan University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zhaohong\",\"middleName\":\"\",\"lastName\":\"Deng\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2024-08-08 07:32:13\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-4879002/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-4879002/v1\",\"draftVersion\":[],\"editorialEvents\":[{\"content\":\"https://doi.org/10.1007/s00530-025-01669-w\",\"type\":\"published\",\"date\":\"2025-01-29T15:57:11+00:00\"}],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":75351400,\"identity\":\"0fa7b836-3700-48f7-8a4c-68cc9cc7e5cf\",\"added_by\":\"auto\",\"created_at\":\"2025-02-03 16:10:41\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":3630361,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Foodimagesegmentationbasedondeepandshallowdualbranchnetwork.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-4879002/v1_covered_e7a3ee5e-4904-4c7e-9d02-68befe35eba7.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Food Image Segmentation based on Deep and Shallow Dual-branch Network\",\"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\":\"info@researchsquare.com\",\"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\":\"Food image segmentation, Deep learning, Swin Transformer, Food health, Multi-scale feature fusion\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-4879002/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-4879002/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Food image segmentation is an important research area within the fields of computer vision and machine learning. Traditional methods often input high-resolution food images at large sizes directly into network models, which leads to high computational costs. Additionally, effectively distinguishing between different foods with similar appearances and the same food in different forms poses a significant challenge. This paper introduces a dual-branch structure network based on Swin Transformer and convolutional neural networks (FDSNet), which significantly reduces the computational costs of processing large-size input images. Furthermore, this study introduces a multi-scale feature fusion technique that effectively integrates feature information from different scales and levels, enabling the model to more accurately segment and recognize different foods. Our method can more precisely perform food image segmentation, helping people improve their diets and manage health better. Training and testing on the FoodSeg103 and UECFoodPixComplete public food datasets have shown that our model achieves mean Intersection over Union (IoU) scores of 47.34 and 75.89, respectively, demonstrating higher accuracy and computational efficiency compared to other methods.\",\"manuscriptTitle\":\"Food Image Segmentation based on Deep and Shallow Dual-branch Network\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2024-10-09 04:06:31\",\"doi\":\"10.21203/rs.3.rs-4879002/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2024-11-06T00:11:43+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2024-10-17T07:30:04+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"123352257302922032200052331352383160817\",\"date\":\"2024-10-09T13:33:17+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2024-09-24T01:31:06+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"275060961369230257955731640697461565462\",\"date\":\"2024-09-23T00:38:03+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"336981579461458470505281223548666948391\",\"date\":\"2024-09-16T06:27:57+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2024-09-11T06:01:50+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2024-09-06T03:08:57+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2024-08-09T07:49:38+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Multimedia Systems\",\"date\":\"2024-08-08T07:30:56+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"8824e792-eb8f-4bb8-9401-6fe28de0201c\",\"owner\":[],\"postedDate\":\"October 9th, 2024\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"published-in-journal\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-02-03T16:05:09+00:00\",\"versionOfRecord\":{\"articleIdentity\":\"rs-4879002\",\"link\":\"https://doi.org/10.1007/s00530-025-01669-w\",\"journal\":{\"identity\":\"multimedia-systems\",\"isVorOnly\":false,\"title\":\"Multimedia Systems\"},\"publishedOn\":\"2025-01-29 15:57:11\",\"publishedOnDateReadable\":\"January 29th, 2025\"},\"versionCreatedAt\":\"2024-10-09 04:06:31\",\"video\":\"\",\"vorDoi\":\"10.1007/s00530-025-01669-w\",\"vorDoiUrl\":\"https://doi.org/10.1007/s00530-025-01669-w\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-4879002\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-4879002\",\"identity\":\"rs-4879002\",\"version\":[\"v1\"]},\"buildId\":\"qtupq5eGEP_6zYnWcrvyt\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}