{"id":"https://openalex.org/W2981353851","doi":"https://doi.org/10.1145/3322905.3322916","title":"Labelling OCR Ground Truth for Usage in Repositories","display_name":"Labelling OCR Ground Truth for Usage in Repositories","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2981353851","doi":"https://doi.org/10.1145/3322905.3322916","mag":"2981353851"},"language":"en","primary_location":{"id":"doi:10.1145/3322905.3322916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322905.3322916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068411984","display_name":"Matthias Boenig","orcid":"https://orcid.org/0000-0003-4615-4753"},"institutions":[{"id":"https://openalex.org/I23277345","display_name":"Berlin-Brandenburg Academy of Sciences and Humanities","ror":"https://ror.org/05jgq9443","country_code":"DE","type":"education","lineage":["https://openalex.org/I23277345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Boenig","raw_affiliation_strings":["Berlin-Brandenburg Academy of Sciences and Humanities, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin-Brandenburg Academy of Sciences and Humanities, Berlin, Germany","institution_ids":["https://openalex.org/I23277345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061484718","display_name":"Konstantin Baierer","orcid":"https://orcid.org/0000-0003-2397-242X"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konstantin Baierer","raw_affiliation_strings":["Berlin State Library - Prussian Cultural Heritage, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin State Library - Prussian Cultural Heritage, Berlin, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085905087","display_name":"Volker Hartmann","orcid":"https://orcid.org/0000-0001-6383-5214"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Hartmann","raw_affiliation_strings":["Karlsruhe Institute of Technology (KIT), Steinbuch Centre for Computing, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT), Steinbuch Centre for Computing, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011418539","display_name":"Maria Federbusch","orcid":null},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maria Federbusch","raw_affiliation_strings":["Berlin State Library - Prussian Cultural Heritage, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin State Library - Prussian Cultural Heritage, Berlin, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060385793","display_name":"Clemens Neudecker","orcid":"https://orcid.org/0000-0001-5293-8322"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Staatsbibliothek zu Berlin","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens Neudecker","raw_affiliation_strings":["Berlin State Library - Prussian Cultural Heritage, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berlin State Library - Prussian Cultural Heritage, Berlin, Germany","institution_ids":["https://openalex.org/I2802918869"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2171,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93157536,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.8591093420982361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663494348526001},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7128986120223999},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6974342465400696},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6772903800010681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.668001651763916},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4804622530937195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41898778080940247},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17414456605911255}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8591093420982361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663494348526001},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7128986120223999},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6974342465400696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6772903800010681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.668001651763916},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4804622530937195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41898778080940247},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17414456605911255}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3322905.3322916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3322905.3322916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G8042784898","display_name":null,"funder_award_id":"409784275","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1989737761","https://openalex.org/W2586232744","https://openalex.org/W2760962973","https://openalex.org/W2787677190","https://openalex.org/W2804438980","https://openalex.org/W2943583939"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281","https://openalex.org/W4295532600"],"abstract_inverted_index":{"The":[0],"rapid":[1],"developments":[2],"in":[3],"deep/machine":[4],"learning":[5],"algorithms":[6],"have":[7],"over":[8],"the":[9],"last":[10],"decade":[11],"largely":[12],"replaced":[13],"traditional":[14],"pattern/language-based":[15],"approaches":[16],"to":[17,48],"OCR.":[18],"Training":[19],"these":[20],"new":[21],"tools":[22],"requires":[23],"scanned":[24],"images":[25],"alongside":[26],"their":[27],"transcriptions":[28],"(Ground":[29],"Truth,":[30],"GT).":[31],"To":[32],"OCR":[33],"historical":[34],"documents":[35],"with":[36],"high":[37],"accuracy,":[38],"a":[39],"wide":[40],"variety":[41],"and":[42],"variability":[43],"of":[44],"GT":[45],"is":[46],"required":[47],"create":[49],"highly":[50],"specific":[51,54],"models":[52],"for":[53],"document":[55],"corpora.":[56]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}