{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/calamari-a-high-performance-tensorflow-based","title":"Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition","arxiv_id":"1807.02004","date":"2018-07-05","proceeding":null,"authors":["Christoph Wick","Christian Reul","Frank Puppe"],"abstract":"Optical Character Recognition (OCR) on contemporary and historical data is\nstill in the focus of many researchers. Especially historical prints require\nbook specific trained OCR models to achieve applicable results (Springmann and\nL\\\"udeling, 2016, Reul et al., 2017a). To reduce the human effort for manually\nannotating ground truth (GT) various techniques such as voting and pretraining\nhave shown to be very efficient (Reul et al., 2018a, Reul et al., 2018b).\nCalamari is a new open source OCR line recognition software that both uses\nstate-of-the art Deep Neural Networks (DNNs) implemented in Tensorflow and\ngiving native support for techniques such as pretraining and voting. The\ncustomizable network architectures constructed of Convolutional Neural Networks\n(CNNS) and Long-ShortTerm-Memory (LSTM) layers are trained by the so-called\nConnectionist Temporal Classification (CTC) algorithm of Graves et al. (2006).\nOptional usage of a GPU drastically reduces the computation times for both\ntraining and prediction. We use two different datasets to compare the\nperformance of Calamari to OCRopy, OCRopus3, and Tesseract 4. Calamari reaches\na Character Error Rate (CER) of 0.11% on the UW3 dataset written in modern\nEnglish and 0.18% on the DTA19 dataset written in German Fraktur, which\nconsiderably outperforms the results of the existing softwares.","url_abs":"http://arxiv.org/abs/1807.02004v3","url_pdf":"http://arxiv.org/pdf/1807.02004v3.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":"calamari-a-high-performance-tensorflow-based","repo_url":"https://github.com/chreul/mptv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"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":"https://syntology.ai/paper/1807.02004","atlas_url":"https://app.syntology.ai/?focus=1807.02004","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1807.02004"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.02004\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.02004"},"call":"get_concepts_for_paper(arxiv_id=\"1807.02004\")"}],"by_repo":[{"repo":"chreul/mptv","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e717a827a4fefae61399885b2704c886ee9ceb55dcf5de7d73b63dbcf7d059c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}