{"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/improving-ocr-accuracy-on-early-printed-books-1","title":"Improving OCR Accuracy on Early Printed Books using Deep Convolutional Networks","arxiv_id":"1802.10033","date":"2018-02-27","proceeding":null,"authors":["Christoph Wick","Christian Reul","Frank Puppe"],"abstract":"This paper proposes a combination of a convolutional and a LSTM network to\nimprove the accuracy of OCR on early printed books. While the standard model of\nline based OCR uses a single LSTM layer, we utilize a CNN- and Pooling-Layer\ncombination in advance of an LSTM layer. Due to the higher amount of trainable\nparameters the performance of the network relies on a high amount of training\nexamples to unleash its power. Hereby, the error is reduced by a factor of up\nto 44%, yielding a CER of 1% and below. To further improve the results we use a\nvoting mechanism to achieve character error rates (CER) below $0.5%$. The\nruntime of the deep model for training and prediction of a book behaves very\nsimilar to a shallow network.","url_abs":"http://arxiv.org/abs/1802.10033v1","url_pdf":"http://arxiv.org/pdf/1802.10033v1.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":"improving-ocr-accuracy-on-early-printed-books-1","repo_url":"https://github.com/ChWick/ocropy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}