{"id":"https://openalex.org/W2286176598","doi":"https://doi.org/10.1145/2809544.2809554","title":"Europeana Newspapers OCR Workflow Evaluation","display_name":"Europeana Newspapers OCR Workflow Evaluation","publication_year":2015,"publication_date":"2015-08-22","ids":{"openalex":"https://openalex.org/W2286176598","doi":"https://doi.org/10.1145/2809544.2809554","mag":"2286176598"},"language":"en","primary_location":{"id":"doi:10.1145/2809544.2809554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2809544.2809554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2809544.2809554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2809544.2809554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017391408","display_name":"Stefan Pletschacher","orcid":"https://orcid.org/0000-0003-0541-0968"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stefan Pletschacher","raw_affiliation_strings":["Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061198957","display_name":"Christian Clausner","orcid":"https://orcid.org/0000-0001-6041-1002"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian Clausner","raw_affiliation_strings":["Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033674031","display_name":"Apostolos Antonacopoulos","orcid":"https://orcid.org/0000-0001-9552-0233"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Apostolos Antonacopoulos","raw_affiliation_strings":["Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Image Analysis (PRImA) Research Lab, School of Computing, Science and Engineering, University of Salford, Greater Manchester, United Kingdom","institution_ids":["https://openalex.org/I54459138"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017391408"],"corresponding_institution_ids":["https://openalex.org/I54459138"],"apc_list":null,"apc_paid":null,"fwci":1.8753,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90778055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9937999844551086,"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"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.991100013256073,"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/workflow","display_name":"Workflow","score":0.8849707841873169},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.8807418942451477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639893293380737},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5907752513885498},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5905137658119202},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5200110077857971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47296684980392456},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43606215715408325},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4041183590888977},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3211711645126343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3034324049949646},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23852160573005676},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07575103640556335},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.0683203637599945},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06608694791793823}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8849707841873169},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.8807418942451477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639893293380737},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5907752513885498},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5905137658119202},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5200110077857971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47296684980392456},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43606215715408325},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4041183590888977},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3211711645126343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3034324049949646},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23852160573005676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07575103640556335},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0683203637599945},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06608694791793823},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2809544.2809554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2809544.2809554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2809544.2809554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:usir.salford.ac.uk:37655","is_oa":true,"landing_page_url":"http://usir.salford.ac.uk/id/eprint/37655/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401501","display_name":"University of Salford Institutional Repository (University of Salford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54459138","host_organization_name":"University of Salford","host_organization_lineage":["https://openalex.org/I54459138"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"doi:10.1145/2809544.2809554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2809544.2809554","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2809544.2809554","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3473489244","display_name":null,"funder_award_id":"297380","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2286176598.pdf","grobid_xml":"https://content.openalex.org/works/W2286176598.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1968030024","https://openalex.org/W2005173844","https://openalex.org/W2013848960","https://openalex.org/W2016234256","https://openalex.org/W2040799618","https://openalex.org/W2061822043","https://openalex.org/W2063420976","https://openalex.org/W2106311500","https://openalex.org/W2124410444","https://openalex.org/W2149128132","https://openalex.org/W2503697509","https://openalex.org/W7011133798","https://openalex.org/W7047636377","https://openalex.org/W7075269551"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W2100945520","https://openalex.org/W2386525189","https://openalex.org/W2360284199","https://openalex.org/W2620505790"],"abstract_inverted_index":{"This":[0],"paper":[1],"summarises":[2],"the":[3,9,19,30,65,90,101],"final":[4],"performance":[5],"evaluation":[6],"results":[7],"of":[8,28,38,76],"OCR":[10,119],"workflow":[11,104],"which":[12,43,59],"was":[13,46],"employed":[14,91],"for":[15],"large-scale":[16],"production":[17,103],"in":[18,70,82],"Europeana":[20],"Newspapers":[21],"project.":[22],"It":[23],"gives":[24],"a":[25,35],"detailed":[26],"overview":[27],"how":[29,64],"involved":[31],"software":[32],"performed":[33],"on":[34,63,114],"representative":[36],"dataset":[37],"historical":[39],"newspaper":[40],"pages":[41],"(for":[42],"ground":[44],"truth":[45],"created)":[47],"with":[48],"regard":[49],"to":[50,84,89,100,107,118],"general":[51],"text":[52],"accuracy":[53],"as":[54,56],"well":[55],"layout-related":[57],"factors":[58],"have":[60],"an":[61],"impact":[62],"material":[66],"can":[67],"be":[68],"used":[69],"specific":[71],"use":[72],"scenarios.":[73],"Specific":[74],"types":[75],"errors":[77],"are":[78,105],"examined":[79],"and":[80,95,111],"evaluated":[81],"order":[83],"identify":[85],"possible":[86],"improvements":[87],"related":[88,117],"document":[92],"image":[93],"analysis":[94],"recognition":[96],"methods.":[97],"Moreover,":[98],"alternatives":[99],"standard":[102],"assessed":[106],"determine":[108],"future":[109],"directions":[110],"give":[112],"advice":[113],"best":[115],"practice":[116],"projects.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
