{"paper_id":"0b04d77a-efce-4c4f-a270-d57e511fbadd","body_text":"OG-HFYOLO: Orientation Gradient guidance and Heterogeneous feature fusion for deformation table cell instance segmentation | 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 OG-HFYOLO: Orientation Gradient guidance and Heterogeneous feature fusion for deformation table cell instance segmentation Long Liu, CiHui Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7187132/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Table structure recognition is a key task in document analysis.However, geometric deformations in deformed tables weaken the correlation between content and structural information, thereby hindering downstream tasks’ ability to extract accurate content. To address this challenge, we propose the OG-HFYOLO model for fine-grained cell coordinate localization. The model integrates a Gradient-Orientation-Aware Extractor to enhance edge detection and introduces Heterogeneous Kernel Cross Fusion module to boost multi-scale feature learning, improving feature expression accuracy. Combined with a Scale-aware Loss function for better scale feature adaptation during training and mask-driven non-maximal suppression replacing traditional bounding-box suppression post-processing, the model achieves refined feature representation and superior localization performance. We further propose a data generator to address dataset limitations for fine-grained deformation table cell localization and construct the large-scale Deformation Wired Table (DWTAL) dataset. Experiments demonstrate that OG-HFYOLO achieves superior segmentation accuracy compared to all mainstream instance segmentation models on the DWTAL dataset. The dataset and the source code are open source: https://github.com/justliulong/OGHFYOLO. Deformation table cell localization Instance segmentation Gradient Orientation-aware Extractor Heterogeneous Kernel Cross Fusion Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Jul, 2025 Reviewers invited by journal 27 Jul, 2025 Editor assigned by journal 25 Jul, 2025 Submission checks completed at journal 25 Jul, 2025 First submitted to journal 22 Jul, 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-7187132\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":491560203,\"identity\":\"d28c3d34-52cc-45a6-a284-1097d5f5989e\",\"order_by\":0,\"name\":\"Long Liu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"School of Information Engineering, Nanchang Hangkong University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Long\",\"middleName\":\"\",\"lastName\":\"Liu\",\"suffix\":\"\"},{\"id\":491560204,\"identity\":\"cb0aa909-7aa6-4df9-a5b3-be8f7a19a89a\",\"order_by\":1,\"name\":\"CiHui Yang\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYNACgwMMbOwNDMxgzgGitfAcIEkLSJlEApFaDI6fPfziR8GdxD7Jtwc/F7YxyPHdSGD8XIBPy5m8NMseg2eJbdJ5ydIz2xiMJW8kMEvPwOuLHDNjBoPDQC05Zsy8bQyJG24ksDHz4NNy/g1Ui+QZsJZ6wlpu5Bg/BmuR4AFrSTAgpEXyxhszxh6Dw8ZtPDnG0jznJAxnnnnYLI1PC9/5HOMPP/4clp3ffsbwM0+ZjTzf8eSDn/FpUQBGogQSH8RmbMCjgYFBHphMPuBVMQpGwSgYBaMAABVFTCPh7jW+AAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"School of Information Engineering, Nanchang Hangkong University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"CiHui\",\"middleName\":\"\",\"lastName\":\"Yang\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-07-22 12:38:30\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7187132/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7187132/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":88023179,\"identity\":\"9ed49b0b-33ac-48f1-a5c3-c02e222a4f4f\",\"added_by\":\"auto\",\"created_at\":\"2025-07-31 14:13:28\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":11654971,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Springertemplate.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7187132/v1_covered_61aa79b9-3cac-4d24-b8cf-87bba19b87a8.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"OG-HFYOLO: Orientation Gradient guidance and Heterogeneous feature fusion for deformation table cell instance segmentation\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Deformation table cell localization, Instance segmentation, Gradient Orientation-aware Extractor, Heterogeneous Kernel Cross Fusion\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7187132/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7187132/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eTable structure recognition is a key task in document analysis.However, geometric deformations in deformed tables weaken the correlation between content and structural information, thereby hindering downstream tasks’ ability to extract accurate content. To address this challenge, we propose the OG-HFYOLO model for fine-grained cell coordinate localization. The model integrates a Gradient-Orientation-Aware Extractor to enhance edge detection and introduces Heterogeneous Kernel Cross Fusion module to boost multi-scale feature learning, improving feature expression accuracy. Combined with a Scale-aware Loss function for better scale feature adaptation during training and mask-driven non-maximal suppression replacing traditional bounding-box suppression post-processing, the model achieves refined feature representation and superior localization performance. We further propose a data generator to address dataset limitations for fine-grained deformation table cell localization and construct the large-scale Deformation Wired Table (DWTAL) dataset. Experiments demonstrate that OG-HFYOLO achieves superior segmentation accuracy compared to all mainstream instance segmentation models on the DWTAL dataset. The dataset and the source code are open source: https://github.com/justliulong/OGHFYOLO.\\u003c/p\\u003e\",\"manuscriptTitle\":\"OG-HFYOLO: Orientation Gradient guidance and Heterogeneous feature fusion for deformation table cell instance segmentation\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-07-31 13:49:13\",\"doi\":\"10.21203/rs.3.rs-7187132/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2025-07-27T19:16:41+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-07-27T19:15:59+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-07-25T16:11:51+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-07-25T16:11:46+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Signal, Image and Video Processing\",\"date\":\"2025-07-22T12:35:53+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"84cc928c-398e-47d6-b853-06fb5fb8816a\",\"owner\":[],\"postedDate\":\"July 31st, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-08-10T21:08:14+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-07-31 13:49:13\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7187132\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7187132\",\"identity\":\"rs-7187132\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}