{"id":37615142,"url":"https://github.com/jiangnanboy/table_structure_recognition","last_synced_at":"2026-01-16T10:29:45.220Z","repository":{"id":283909823,"uuid":"762275454","full_name":"jiangnanboy/table_structure_recognition","owner":"jiangnanboy","description":"利用Swin-Unet(Swin Transformer Unet)实现对文档图片里表格结构的识别，Swin-unet (Swin Transformer Unet) is used to identify the document table structure","archived":false,"fork":false,"pushed_at":"2024-02-23T12:50:24.000Z","size":5575,"stargazers_count":16,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-18T13:49:41.176Z","etag":null,"topics":["swin-transformer-unet","swin-unet","table-recognition","table-structure-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jiangnanboy.png","metadata":{"files":{"readme":"README.en.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-23T12:49:38.000Z","updated_at":"2025-03-12T03:01:34.000Z","dependencies_parsed_at":"2025-03-23T01:02:24.608Z","dependency_job_id":"e8400f31-43c3-40b4-baa2-e208696080c5","html_url":"https://github.com/jiangnanboy/table_structure_recognition","commit_stats":null,"previous_names":["jiangnanboy/table_structure_recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jiangnanboy/table_structure_recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiangnanboy%2Ftable_structure_recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiangnanboy%2Ftable_structure_recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiangnanboy%2Ftable_structure_recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiangnanboy%2Ftable_structure_recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jiangnanboy","download_url":"https://codeload.github.com/jiangnanboy/table_structure_recognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiangnanboy%2Ftable_structure_recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28478050,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-16T06:30:42.265Z","status":"ssl_error","status_checked_at":"2026-01-16T06:30:16.248Z","response_time":107,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["swin-transformer-unet","swin-unet","table-recognition","table-structure-recognition"],"created_at":"2026-01-16T10:29:45.146Z","updated_at":"2026-01-16T10:29:45.208Z","avatar_url":"https://github.com/jiangnanboy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[简体中文](README.md) | English\n# Swin-unet (Swin Transformer Unet) is used to identify the document table structure \n![](img/architecture.png) \n## function   \n- [x] Identify the lines in the doc table\n- [ ] Convert results to excel\n\n## download the weights model file   \nModel file address：https://pan.baidu.com/s/1K2bxqqmZaOtPI1jeWN3Ygg \n\npassword：w0yj\n\nCopy the model.h5 to the model directory\n\n## training（tensorflow2.5）     \nSee train.py in this project    \n\n## prediction\nSee table_line_infer.py in this project\n\n## identification result presentation\n![](img/2.jpg) \n### table line detection\n![](img/2_line.png) \n\n![](img/3.jpg) \n### table line detection\n![](img/3_line.png) \n\n![](img/8.jpg) \n### table line detection\n![](img/8_line.png) \n\n![](img/dd.jpg) \n### table line detection\n![](img/dd_line.png) \n\n![](img/plane.png) \n### table line detection\n![](img/plane_line.png)\n\n![](img/table.png) \n### table line detection\n![](img/table_line.png)    \n\n## contact\n\n1、github：https://github.com/jiangnanboy\n\n2、blog：https://www.cnblogs.com/little-horse/\n\n3、QQ:2229029156\n   \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiangnanboy%2Ftable_structure_recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjiangnanboy%2Ftable_structure_recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiangnanboy%2Ftable_structure_recognition/lists"}