{"id":"https://openalex.org/W3023805750","doi":"https://doi.org/10.1007/s00521-020-04910-x","title":"Building an efficient OCR system for historical documents with little training data","display_name":"Building an efficient OCR system for historical documents with little training data","publication_year":2020,"publication_date":"2020-05-09","ids":{"openalex":"https://openalex.org/W3023805750","doi":"https://doi.org/10.1007/s00521-020-04910-x","mag":"3023805750"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-020-04910-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-020-04910-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-020-04910-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-020-04910-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087839927","display_name":"Ji\u0159\u0131\u0301 Mart\u0131\u0301nek","orcid":"https://orcid.org/0000-0003-2981-1723"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed Mart\u00ednek","raw_affiliation_strings":["Department of Computer Science and Engineering, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089368966","display_name":"Ladislav Lenc","orcid":"https://orcid.org/0000-0002-1066-7269"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Lenc","raw_affiliation_strings":["NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062260796","display_name":"Pavel Kr\u00e1l","orcid":"https://orcid.org/0000-0002-3096-675X"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Pavel Kr\u00e1l","raw_affiliation_strings":["Department of Computer Science and Engineering, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic","NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]},{"raw_affiliation_string":"NTIS - New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062260796"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":3.2001,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.92745603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"32","issue":"23","first_page":"17209","last_page":"17227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9919000267982483,"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.8848875761032104},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8515112400054932},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6363586187362671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5826790928840637},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.5637635588645935},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5288525819778442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133504271507263},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5028888583183289},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.48209741711616516},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.47445616126060486},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.46016284823417664},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44987690448760986},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4239032566547394},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4050676226615906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32256579399108887},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27454298734664917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8848875761032104},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8515112400054932},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6363586187362671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5826790928840637},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.5637635588645935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5288525819778442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133504271507263},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5028888583183289},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.48209741711616516},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.47445616126060486},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.46016284823417664},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44987690448760986},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4239032566547394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4050676226615906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32256579399108887},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27454298734664917},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00521-020-04910-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-020-04910-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-020-04910-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dspace5.zcu.cz:11025/42814","is_oa":false,"landing_page_url":"http://hdl.handle.net/11025/42814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400586","display_name":"Digital Library (University of West Bohemia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92715842","host_organization_name":"University of West Bohemia in Pilsen","host_organization_lineage":["https://openalex.org/I92715842"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"\u010dl\u00e1nek"}],"best_oa_location":{"id":"doi:10.1007/s00521-020-04910-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-020-04910-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-020-04910-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G176604203","display_name":null,"funder_award_id":"02.1.01/0.0/0.0","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G1888088267","display_name":null,"funder_award_id":"2014-2020\u2019","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2093725072","display_name":null,"funder_award_id":"CZ.02.1.01/0.0/0.0/17_048/000 7267","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2859222468","display_name":null,"funder_award_id":"CZ.02.1.01/0.0/0.0/17\u02d9048/0007267","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G291036901","display_name":null,"funder_award_id":"CZ.02","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3490171961","display_name":null,"funder_award_id":"CZ.02.1.01","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4280972364","display_name":null,"funder_award_id":"CZ.02.1.01/0.0","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5916014575","display_name":null,"funder_award_id":"CZ.02.1.01/0.0/0.0","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023805750.pdf","grobid_xml":"https://content.openalex.org/works/W3023805750.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W99399284","https://openalex.org/W845365781","https://openalex.org/W1491389626","https://openalex.org/W1523191460","https://openalex.org/W1533861849","https://openalex.org/W1538131130","https://openalex.org/W1888914491","https://openalex.org/W1901129140","https://openalex.org/W1922126009","https://openalex.org/W1993557076","https://openalex.org/W2060580591","https://openalex.org/W2064675550","https://openalex.org/W2085361026","https://openalex.org/W2099106019","https://openalex.org/W2106311500","https://openalex.org/W2127141656","https://openalex.org/W2133059825","https://openalex.org/W2133098817","https://openalex.org/W2133564696","https://openalex.org/W2149128132","https://openalex.org/W2150102617","https://openalex.org/W2161381512","https://openalex.org/W2194187530","https://openalex.org/W2284482567","https://openalex.org/W2317505761","https://openalex.org/W2395611524","https://openalex.org/W2768926640","https://openalex.org/W2773536003","https://openalex.org/W2775795276","https://openalex.org/W2785875661","https://openalex.org/W2786019807","https://openalex.org/W2786956341","https://openalex.org/W2787480186","https://openalex.org/W2798904333","https://openalex.org/W2962707697","https://openalex.org/W2962790387","https://openalex.org/W2963073614","https://openalex.org/W2963150697","https://openalex.org/W2963890275","https://openalex.org/W3004299970","https://openalex.org/W3104637907","https://openalex.org/W3105988348","https://openalex.org/W4249179470","https://openalex.org/W6610385870"],"related_works":["https://openalex.org/W2218402054","https://openalex.org/W4383988422","https://openalex.org/W2168844671","https://openalex.org/W4385079034","https://openalex.org/W2784287639","https://openalex.org/W3023805750","https://openalex.org/W4294702218","https://openalex.org/W3046471831","https://openalex.org/W2189110401","https://openalex.org/W2007589418"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"the":[2,12,32,46,60,131,143,146,182,202,211,229],"number":[3],"of":[4,24,70,79,95,142,215,231],"digitized":[5],"historical":[6,61,87,251],"documents":[7,252],"has":[8],"increased":[9],"rapidly":[10],"during":[11],"last":[13],"a":[14,67,77,92,152,191,241,254,258],"few":[15,192],"decades,":[16],"it":[17],"is":[18,164],"necessary":[19],"to":[20,30,59,206,244],"provide":[21],"efficient":[22,247],"methods":[23,36,54,80,123,172],"information":[25],"retrieval":[26],"and":[27,116,119,130,169,184],"knowledge":[28],"extraction":[29],"make":[31],"data":[33,195],"accessible.":[34],"Such":[35],"are":[37,55,124,140,173,187,223],"dependent":[38],"on":[39,86,126,175],"optical":[40],"character":[41],"recognition":[42],"(OCR)":[43],"which":[44],"converts":[45],"document":[47,88],"images":[48,89],"into":[49],"textual":[50],"representations.":[51],"Nowadays,":[52],"OCR":[53,85,104,132,157,185,248],"often":[56],"not":[57],"adapted":[58],"domain;":[62],"moreover,":[63],"they":[64],"usually":[65],"need":[66,255],"significant":[68],"amount":[69,94],"annotated":[71,98,193,260],"documents.":[72],"Therefore,":[73],"this":[74,238],"paper":[75,239],"introduces":[76],"set":[78,214],"that":[81,180,220],"allows":[82],"performing":[83],"an":[84,246],"using":[90],"only":[91,190,257],"small":[93,213],"real,":[96],"manually":[97],"training":[99,261],"data.":[100,177,216,262],"The":[101,197],"presented":[102],"complete":[103],"system":[105,249],"includes":[106],"two":[107],"main":[108],"tasks:":[109],"page":[110],"layout":[111],"analysis":[112],"including":[113],"text":[114],"block":[115],"line":[117],"segmentation":[118,122,183],"OCR.":[120],"Our":[121],"based":[125],"fully":[127],"convolutional":[128],"networks,":[129],"approach":[133],"utilizes":[134],"recurrent":[135],"neural":[136],"networks.":[137],"Both":[138],"approaches":[139],"state":[141],"art":[144],"in":[145],"relevant":[147],"fields.":[148],"We":[149,178,217],"have":[150],"created":[151],"novel":[153],"real":[154,194],"dataset":[155],"for":[156,167,250,256],"from":[158],"Porta":[159],"fontium":[160],"portal.":[161],"This":[162],"corpus":[163],"freely":[165],"available":[166],"research,":[168],"all":[170],"proposed":[171],"evaluated":[174],"these":[176],"show":[179],"both":[181],"tasks":[186],"feasible":[188],"with":[189,210,253],"samples.":[196],"experiments":[198],"aim":[199],"at":[200],"determining":[201],"best":[203],"way":[204,242],"how":[205,243],"achieve":[207],"good":[208],"performance":[209],"given":[212],"also":[218],"demonstrate":[219],"obtained":[221],"scores":[222,230],"comparable":[224],"or":[225],"even":[226],"better":[227],"than":[228],"several":[232],"state-of-the-art":[233],"systems.":[234],"To":[235],"sum":[236],"up,":[237],"shows":[240],"create":[245],"little":[259]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}