{"id":"https://openalex.org/W3081407480","doi":"https://doi.org/10.1007/s10032-020-00359-9","title":"Optical character recognition with neural networks and post-correction with finite state methods","display_name":"Optical character recognition with neural networks and post-correction with finite state methods","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3081407480","doi":"https://doi.org/10.1007/s10032-020-00359-9","mag":"3081407480"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-020-00359-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-020-00359-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-020-00359-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","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/s10032-020-00359-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028952369","display_name":"Senka Drobac","orcid":"https://orcid.org/0000-0002-7645-3079"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Senka Drobac","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7645-3079","affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001408607","display_name":"Krister Lind\u00e9n","orcid":"https://orcid.org/0000-0003-2337-303X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Krister Lind\u00e9n","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028952369"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.923,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.94915535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":"4","first_page":"279","last_page":"295"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8787119388580322},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8666648268699646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6314678192138672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5904349088668823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5801392793655396},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5718553066253662},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5358906984329224},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.5215727686882019},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5187714099884033},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4947297275066376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4250320494174957},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41576170921325684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39404040575027466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8787119388580322},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8666648268699646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6314678192138672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5904349088668823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5801392793655396},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5718553066253662},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5358906984329224},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.5215727686882019},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5187714099884033},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4947297275066376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4250320494174957},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41576170921325684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39404040575027466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10032-020-00359-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-020-00359-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-020-00359-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/325628","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/325628","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10032-020-00359-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-020-00359-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-020-00359-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"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":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310086","display_name":"Helsingin Yliopisto","ror":"https://ror.org/040af2s02"},{"id":"https://openalex.org/F4320310467","display_name":"Helsingin ja Uudenmaan Sairaanhoitopiiri","ror":"https://ror.org/020cpqb94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081407480.pdf","grobid_xml":"https://content.openalex.org/works/W3081407480.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1647671624","https://openalex.org/W1990871427","https://openalex.org/W1993557076","https://openalex.org/W2004920872","https://openalex.org/W2024348326","https://openalex.org/W2032223184","https://openalex.org/W2060580591","https://openalex.org/W2063828767","https://openalex.org/W2064726190","https://openalex.org/W2088483389","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2171950509","https://openalex.org/W2336079135","https://openalex.org/W2337045451","https://openalex.org/W2404273937","https://openalex.org/W2510006552","https://openalex.org/W2541388296","https://openalex.org/W2568968496","https://openalex.org/W2577375704","https://openalex.org/W2583190795","https://openalex.org/W2584641794","https://openalex.org/W2732430615","https://openalex.org/W2735998760","https://openalex.org/W2798485145","https://openalex.org/W2805770332","https://openalex.org/W2947783142","https://openalex.org/W2955559629","https://openalex.org/W2964322605","https://openalex.org/W2980063486","https://openalex.org/W2982000084","https://openalex.org/W2983390508","https://openalex.org/W2988898388","https://openalex.org/W2990118374","https://openalex.org/W3010233573","https://openalex.org/W3013597222","https://openalex.org/W6629647619"],"related_works":["https://openalex.org/W2789943307","https://openalex.org/W2013767392","https://openalex.org/W3190162935","https://openalex.org/W1566315437","https://openalex.org/W2892857623","https://openalex.org/W2595338207","https://openalex.org/W2151348424","https://openalex.org/W2594897229","https://openalex.org/W1973075426","https://openalex.org/W4290708361"],"abstract_inverted_index":{"Abstract":[0],"The":[1,31,107,202,225],"optical":[2],"character":[3,33],"recognition":[4],"(OCR)":[5],"quality":[6],"of":[7,11,37,76,90,104,123,143,146,178,228,235],"the":[8,12,28,38,77,91,94,105,111,114,119,141,176,182,194,215,221,229,232,241,252],"historical":[9],"part":[10],"Finnish":[13,216],"newspaper":[14],"and":[15,24,47,67,126,128,134,198,217,244],"journal":[16],"corpus":[17,115,243],"is":[18,44,116,231],"rather":[19],"low":[20],"for":[21,100,160,240],"reliable":[22],"search":[23],"scientific":[25],"research":[26],"on":[27,181,193,214,220],"OCRed":[29],"data.":[30],"estimated":[32],"error":[34,200],"rate":[35],"(CER)":[36],"corpus,":[39,95],"achieved":[40],"with":[41,59,149,164,185],"commercial":[42],"software,":[43,61],"between":[45],"8":[46],"13%.":[48],"There":[49],"have":[50,79],"been":[51],"earlier":[52],"attempts":[53],"to":[54,81],"train":[55,83,169],"high-quality":[56,170],"OCR":[57,147,183,196],"models":[58,148],"open-source":[60],"like":[62],"Ocropy":[63],"(":[64,69],"https://github.com/tmbdev/ocropy":[65],")":[66],"Tesseract":[68],"https://github.com/tesseract-ocr/tesseract":[70],"),":[71],"but":[72],"so":[73],"far,":[74],"none":[75],"methods":[78],"managed":[80],"successfully":[82,168],"a":[84,144,205,246],"mixed":[85,237],"model":[86,187,239],"that":[87,113,249],"recognizes":[88],"all":[89],"data":[92,162],"in":[93,110,118,129,208,211],"which":[96],"would":[97],"be":[98],"essential":[99],"an":[101,157],"efficient":[102],"re-OCRing":[103],"corpus.":[106],"difficulty":[108],"lies":[109],"fact":[112],"printed":[117],"two":[120,130],"main":[121],"languages":[122],"Finland":[124],"(Finnish":[125],"Swedish)":[127],"font":[131],"families":[132],"(Blackletter":[133],"Antiqua).":[135],"In":[136],"this":[137],"paper,":[138],"we":[139,155,174,190],"explore":[140],"training":[142,166,234],"variety":[145],"deep":[150],"neural":[151],"networks":[152],"(DNN).":[153],"First,":[154],"find":[156],"optimal":[158],"DNN":[159],"our":[161],"and,":[163],"additional":[165],"data,":[167],"mixed-language":[171],"models.":[172],"Furthermore,":[173],"revisit":[175],"effect":[177],"confidence":[179],"voting":[180,247],"results":[184,197,203],"different":[186],"combinations.":[188],"Finally,":[189],"perform":[191,199],"post-correction":[192],"new":[195],"analysis.":[201],"show":[204],"significant":[206],"boost":[207],"accuracy,":[209],"resulting":[210],"1.7%":[212],"CER":[213,219],"2.7%":[218],"Swedish":[222],"test":[223],"set.":[224],"greatest":[226],"accomplishment":[227],"study":[230],"successful":[233],"one":[236],"language":[238],"entire":[242],"finding":[245],"setup":[248],"further":[250],"improves":[251],"results.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}