{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/augraphy-a-data-augmentation-library-for","title":"Augraphy: A Data Augmentation Library for Document Images","arxiv_id":"2208.14558","date":"2022-08-30","proceeding":null,"authors":["Alexander Groleau","Kok Wei Chee","Stefan Larson","Samay Maini","Jonathan Boarman"],"abstract":"This paper introduces Augraphy, a Python library for constructing data augmentation pipelines which produce distortions commonly seen in real-world document image datasets. Augraphy stands apart from other data augmentation tools by providing many different strategies to produce augmented versions of clean document images that appear as if they have been altered by standard office operations, such as printing, scanning, and faxing through old or dirty machines, degradation of ink over time, and handwritten markings. This paper discusses the Augraphy tool, and shows how it can be used both as a data augmentation tool for producing diverse training data for tasks such as document denoising, and also for generating challenging test data to evaluate model robustness on document image modeling tasks.","url_abs":"https://arxiv.org/abs/2208.14558v2","url_pdf":"https://arxiv.org/pdf/2208.14558v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"augraphy-a-data-augmentation-library-for","repo_url":"https://github.com/sparkfish/augraphy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"augraphy-a-data-augmentation-library-for","repo_url":"https://github.com/sparkfish/augraphy-paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"denoising","task_name":"Denoising"}],"methods":[{"method_slug":null,"method_name":"Library"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.14558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.14558"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sparkfish/augraphy-paper","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sparkfish/augraphy","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c7b90e280e5f3a33","entry":"default_augment","repo":"sparkfish/augraphy","repo_kind":"official","path":"augraphy/default/pipeline.py","file_url":"https://github.com/sparkfish/augraphy/blob/HEAD/augraphy/default/pipeline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7b90e280e5f3a33"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}