{"id":22914679,"url":"https://github.com/sdpdas/document-layout-generator-and-segmentation-tool","last_synced_at":"2025-04-15T11:35:45.611Z","repository":{"id":245753145,"uuid":"819126948","full_name":"SDpDas/Document-layout-generator-and-segmentation-tool","owner":"SDpDas","description":"Lists all parts of a document PDF and is a highly scalable with robust code.","archived":false,"fork":false,"pushed_at":"2024-06-24T08:04:06.000Z","size":61588,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T19:37:48.324Z","etag":null,"topics":["analysis","document-classification","numpy","opencv-python","pdf2image","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SDpDas.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-06-23T21:16:40.000Z","updated_at":"2024-10-30T15:24:41.000Z","dependencies_parsed_at":"2024-06-23T22:55:53.900Z","dependency_job_id":null,"html_url":"https://github.com/SDpDas/Document-layout-generator-and-segmentation-tool","commit_stats":null,"previous_names":["sdpdas/document-layout-generator-and-segmentation-tool"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SDpDas%2FDocument-layout-generator-and-segmentation-tool","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SDpDas%2FDocument-layout-generator-and-segmentation-tool/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SDpDas%2FDocument-layout-generator-and-segmentation-tool/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SDpDas%2FDocument-layout-generator-and-segmentation-tool/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SDpDas","download_url":"https://codeload.github.com/SDpDas/Document-layout-generator-and-segmentation-tool/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249061514,"owners_count":21206519,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["analysis","document-classification","numpy","opencv-python","pdf2image","python"],"created_at":"2024-12-14T05:16:07.141Z","updated_at":"2025-04-15T11:35:45.574Z","avatar_url":"https://github.com/SDpDas.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Document Layout Generation \r\n\r\nNote - Install necessary libraries such as opencv-python, pdf2image, img2pdf, numpy etc.\r\n       Download Poppler https://github.com/oschwartz10612/poppler-windows/releases/\r\n\r\n## Description\r\n\r\nThis tool converts any document PDF to its segmented version PDF. \r\n\r\nAll middle work can be found in input and output image folder.\r\n\r\n## How to Use?\r\n\r\n1. Download the ZIP file of the project and open its source folder.\r\n\r\n2. Navigate to layout.py and run it directly or by using \r\n\r\n    ```python\r\n    python layout.py\r\n\r\n3. If you want to use your own document add it to folder and change the path in layout.py\r\n\r\n    ```python\r\n    pdf_file = '...\\\\(PDF_name).pdf'\r\n\r\n4. Observe the results in Processed Files folder.\r\n\r\n## Glossary\r\n\r\n1. input_img : will show all images in openCV format when extracted from PDF. \r\n2. output_img : will show all output images after resizing and object detection is done.\r\n3. output_pdf : will display the resultant PDFs of merged output images.\r\n\r\n# Screenshots:\r\n\r\n![arxiv1](working/output_1.png)\r\n\r\n![arxiv1](working/output_2.png)\r\n\r\n# Created by Sagardeep Das\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsdpdas%2Fdocument-layout-generator-and-segmentation-tool","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsdpdas%2Fdocument-layout-generator-and-segmentation-tool","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsdpdas%2Fdocument-layout-generator-and-segmentation-tool/lists"}