{"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/state-of-the-art-optical-character","title":"State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines","arxiv_id":"1810.03436","date":"2018-10-08","proceeding":null,"authors":["Christian Reul","Uwe Springmann","Christoph Wick","Frank Puppe"],"abstract":"In this paper we evaluate Optical Character Recognition (OCR) of 19th century\nFraktur scripts without book-specific training using mixed models, i.e. models\ntrained to recognize a variety of fonts and typesets from previously unseen\nsources. We describe the training process leading to strong mixed OCR models\nand compare them to freely available models of the popular open source engines\nOCRopus and Tesseract as well as the commercial state of the art system ABBYY.\nFor evaluation, we use a varied collection of unseen data from books, journals,\nand a dictionary from the 19th century. The experiments show that training\nmixed models with real data is superior to training with synthetic data and\nthat the novel OCR engine Calamari outperforms the other engines considerably,\non average reducing ABBYYs character error rate (CER) by over 70%, resulting in\nan average CER below 1%.","url_abs":"http://arxiv.org/abs/1810.03436v1","url_pdf":"http://arxiv.org/pdf/1810.03436v1.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":"state-of-the-art-optical-character","repo_url":"https://github.com/chreul/19th-century-fraktur-OCR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}