{"id":"https://openalex.org/W4318196853","doi":"https://doi.org/10.1007/s00799-023-00345-6","title":"Evaluating and mitigating the impact of OCR errors on information retrieval","display_name":"Evaluating and mitigating the impact of OCR errors on information retrieval","publication_year":2023,"publication_date":"2023-01-26","ids":{"openalex":"https://openalex.org/W4318196853","doi":"https://doi.org/10.1007/s00799-023-00345-6"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-023-00345-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-023-00345-6","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-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/A5034858484","display_name":"Lucas Lima de Oliveira","orcid":"https://orcid.org/0000-0002-6814-6052"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Lima de Oliveira","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005416452","display_name":"Danny Suarez Vargas","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Danny Suarez Vargas","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018548489","display_name":"Ant\u00f4nio Marcelo Azevedo Alexandre","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]},{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ant\u00f4nio Marcelo Azevedo Alexandre","raw_affiliation_strings":["Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","Systems Engineering and Computer Science Program (PESC/COPPE), Federal University of Rio de Janeiro, Rio de Janeiro, RJ, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I32393484"]},{"raw_affiliation_string":"Systems Engineering and Computer Science Program (PESC/COPPE), Federal University of Rio de Janeiro, Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060455697","display_name":"F\u00e1bio Corr\u00eaa Cordeiro","orcid":"https://orcid.org/0000-0001-8068-3996"},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]},{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"F\u00e1bio Corr\u00eaa Cordeiro","raw_affiliation_strings":["Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","School of Applied Mathematics, Getulio Vargas Foundation, Rio de Janeiro, RJ, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I32393484"]},{"raw_affiliation_string":"School of Applied Mathematics, Getulio Vargas Foundation, Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I44202434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036781668","display_name":"Diogo da Silva Magalh\u00e3es Gomes","orcid":"https://orcid.org/0000-0001-9351-7647"},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Diogo da Silva Magalh\u00e3es Gomes","raw_affiliation_strings":["Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I32393484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860876","display_name":"Max de Castro Rodrigues","orcid":null},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Max de Castro Rodrigues","raw_affiliation_strings":["Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I32393484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113605711","display_name":"R\u00e9gis Kruel Romeu","orcid":null},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Regis Kruel Romeu","raw_affiliation_strings":["Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petrobras Research and Development Center (CENPES), Rio de Janeiro, RJ, Brazil","institution_ids":["https://openalex.org/I32393484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037408511","display_name":"Viviane P. Moreira","orcid":"https://orcid.org/0000-0003-4400-054X"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Viviane Pereira Moreira","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-4400-054X","affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5037408511"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":1.884,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87544047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"24","issue":"1","first_page":"45","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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/digitization","display_name":"Digitization","score":0.8972813487052917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.86439049243927},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7374056577682495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6417546272277832},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5483036637306213},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45416125655174255},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.44103509187698364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42940881848335266},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4231563210487366},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3338015377521515},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30223220586776733},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1668902039527893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06649351119995117}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.8972813487052917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86439049243927},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7374056577682495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6417546272277832},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5483036637306213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45416125655174255},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.44103509187698364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42940881848335266},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4231563210487366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3338015377521515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30223220586776733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1668902039527893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06649351119995117},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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":1,"locations":[{"id":"doi:10.1007/s00799-023-00345-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-023-00345-6","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6800000071525574,"display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G3278440217","display_name":null,"funder_award_id":"2017/00752-3","funder_id":"https://openalex.org/F4320322468","funder_display_name":"Petrobras"},{"id":"https://openalex.org/G6418116366","display_name":null,"funder_award_id":"2017/00752-3","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322468","display_name":"Petrobras","ror":"https://ror.org/0235kyq22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1482504747","https://openalex.org/W1541376310","https://openalex.org/W1573345323","https://openalex.org/W1771572948","https://openalex.org/W1870791027","https://openalex.org/W1976951044","https://openalex.org/W1976978162","https://openalex.org/W1978022086","https://openalex.org/W1987932675","https://openalex.org/W1990190154","https://openalex.org/W1990871427","https://openalex.org/W2000020806","https://openalex.org/W2011084371","https://openalex.org/W2015629112","https://openalex.org/W2044830896","https://openalex.org/W2052569738","https://openalex.org/W2073722401","https://openalex.org/W2093168600","https://openalex.org/W2127496540","https://openalex.org/W2279316390","https://openalex.org/W2338029868","https://openalex.org/W2404228453","https://openalex.org/W2786672397","https://openalex.org/W2806527475","https://openalex.org/W2809468489","https://openalex.org/W2900753330","https://openalex.org/W2968567788","https://openalex.org/W2980063486","https://openalex.org/W2982632725","https://openalex.org/W2988898388","https://openalex.org/W3012289950","https://openalex.org/W3015310959","https://openalex.org/W3023805750","https://openalex.org/W3031118452","https://openalex.org/W3049158684","https://openalex.org/W3081407480","https://openalex.org/W3107113245","https://openalex.org/W3107366692","https://openalex.org/W3152861274","https://openalex.org/W3178709966","https://openalex.org/W3187836738","https://openalex.org/W3198691721","https://openalex.org/W3210517762","https://openalex.org/W3215413293","https://openalex.org/W3217756930","https://openalex.org/W4200413077","https://openalex.org/W4226236673","https://openalex.org/W4229370390","https://openalex.org/W4231938405","https://openalex.org/W4236121604","https://openalex.org/W4237342689","https://openalex.org/W4248028495","https://openalex.org/W4283454975","https://openalex.org/W4284682639","https://openalex.org/W6604580260","https://openalex.org/W6636625392"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W2592115649","https://openalex.org/W4322582183","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
