{"id":"https://openalex.org/W2135101905","doi":"https://doi.org/10.3217/jucs-017-01-0064","title":"The Use of Latent Semantic Indexing to Mitigate OCR Effects of Related Document Images","display_name":"The Use of Latent Semantic Indexing to Mitigate OCR Effects of Related Document Images","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2135101905","doi":"https://doi.org/10.3217/jucs-017-01-0064","mag":"2135101905"},"language":"en","primary_location":{"id":"pmh:oai:www.producao.usp.br:BDPI/14973","is_oa":false,"landing_page_url":"http://producao.usp.br/handle/BDPI/14973","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP","raw_type":"publishedVersion"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/7001521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002427825","display_name":"Renato F. Bulc\u00e3o-Neto","orcid":"https://orcid.org/0000-0001-8604-0019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"BULCAO-NETO, Renato F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024056211","display_name":"Jos\u00e9 Antonio Camacho-Guerrero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088975","display_name":"Instituto Brasileiro de Informa\u00e7\u00e3o em Ci\u00eancia e Tecnologia","ror":"https://ror.org/006c42y96","country_code":"BR","type":"facility","lineage":["https://openalex.org/I4210088975"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"CAMACHO-GUERRERO, Jose A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023281010","display_name":"Marcio Branquinho Dutra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088975","display_name":"Instituto Brasileiro de Informa\u00e7\u00e3o em Ci\u00eancia e Tecnologia","ror":"https://ror.org/006c42y96","country_code":"BR","type":"facility","lineage":["https://openalex.org/I4210088975"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"DUTRA, Marcio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"BARREIRO, Alvaro","raw_affiliation_strings":["University of A coru\u00f1a"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of A coru\u00f1a","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"PARAPAR, Javier","raw_affiliation_strings":["University of A coru\u00f1a"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of A coru\u00f1a","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011609969","display_name":"Alessandra Alaniz Macedo","orcid":"https://orcid.org/0000-0001-5271-3086"},"institutions":[{"id":"https://openalex.org/I1331278255","display_name":"Universidade de Ribeir\u00e3o Preto","ror":"https://ror.org/00ey54k21","country_code":"BR","type":"education","lineage":["https://openalex.org/I1331278255"]},{"id":"https://openalex.org/I4210160503","display_name":"Universidade Cruzeiro do Sul","ror":"https://ror.org/05k8pq072","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210160503"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"MACEDO, Alessandra A.","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2575,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60678877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9990000128746033,"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":0.9959999918937683,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9063959121704102},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6988736391067505},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6743004322052002},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6716830134391785},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6034953594207764},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5912070274353027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44778311252593994},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43459439277648926},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.412229061126709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3520359992980957},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32298043370246887},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20770975947380066},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.20173919200897217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9063959121704102},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6988736391067505},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6743004322052002},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6716830134391785},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6034953594207764},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5912070274353027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44778311252593994},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43459439277648926},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.412229061126709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3520359992980957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32298043370246887},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20770975947380066},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.20173919200897217},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":3,"locations":[{"id":"pmh:oai:www.producao.usp.br:BDPI/14973","is_oa":false,"landing_page_url":"http://producao.usp.br/handle/BDPI/14973","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP","raw_type":"publishedVersion"},{"id":"pmh:oai:zenodo.org:7001521","is_oa":true,"landing_page_url":"https://zenodo.org/record/7001521","pdf_url":"https://zenodo.org/record/7001521","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JUCS - Journal of Universal Computer Science 17((1)) 64-80","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.5832","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.5832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jucs.org/jucs_17_1/the_use_of_latent/jucs_17_01_0064_0080_neto.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7001521","is_oa":true,"landing_page_url":"https://zenodo.org/record/7001521","pdf_url":"https://zenodo.org/record/7001521","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JUCS - Journal of Universal Computer Science 17((1)) 64-80","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2021456220","display_name":null,"funder_award_id":"TIN2008-06566-C04-04","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G4620859473","display_name":"ArcaMed: um arcabou\u00e7o para constru\u00e7\u00e3o de sistemas de apoio a diagn\u00f3sticos m\u00e9dicos","funder_award_id":"05/60038-5","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G8133918581","display_name":null,"funder_award_id":"07SIN005206PR","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G8329310653","display_name":"LISI Group - laborat\u00f3rio de desenvolvimento associado","funder_award_id":"05/60729-8","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G8544631003","display_name":null,"funder_award_id":"557976/2008-1","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"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/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320326655","display_name":"Xunta de Galicia","ror":"https://ror.org/0181xnw06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2135101905.pdf","grobid_xml":"https://content.openalex.org/works/W2135101905.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1541376310","https://openalex.org/W1580861175","https://openalex.org/W1606197053","https://openalex.org/W1660390307","https://openalex.org/W1967620643","https://openalex.org/W1976978162","https://openalex.org/W1979346010","https://openalex.org/W1989426855","https://openalex.org/W1990513570","https://openalex.org/W1994518313","https://openalex.org/W1996326746","https://openalex.org/W2021236253","https://openalex.org/W2036824582","https://openalex.org/W2046322280","https://openalex.org/W2050716604","https://openalex.org/W2081142165","https://openalex.org/W2092449865","https://openalex.org/W2093432797","https://openalex.org/W2110933355","https://openalex.org/W2115603438","https://openalex.org/W2141141617","https://openalex.org/W2149470434","https://openalex.org/W2157312470"],"related_works":["https://openalex.org/W2050716604","https://openalex.org/W2119179626","https://openalex.org/W2109183677","https://openalex.org/W1515607803","https://openalex.org/W2022650584","https://openalex.org/W1991298148","https://openalex.org/W199764657","https://openalex.org/W3048557958","https://openalex.org/W2169078822","https://openalex.org/W2101671876","https://openalex.org/W2283697398","https://openalex.org/W2887049885","https://openalex.org/W2007385277","https://openalex.org/W1529012620","https://openalex.org/W1993309640","https://openalex.org/W2498054759","https://openalex.org/W2025807940","https://openalex.org/W23466914","https://openalex.org/W1567502312","https://openalex.org/W1439405941"],"abstract_inverted_index":{"Abstract:":[0],"Due":[1],"to":[2,39,129],"both":[3],"the":[4,13,41,62,101,104,131,140,150,158],"widespread":[5],"and":[6,12,28,55,71,80,94],"multipurpose":[7],"use":[8],"of":[9,16,20,44,65,103,133,152,160],"document":[10,21,47,73,91,116,121],"images":[11,22,48,74,84,92],"current":[14],"availability":[15],"a":[17],"high":[18,166],"number":[19],"repositories,":[23,93],"robust":[24],"information":[25],"retrieval":[26],"mechanisms":[27],"systems":[29],"have":[30],"been":[31],"increasingly":[32],"demanded.":[33],"This":[34],"paper":[35],"presents":[36],"an":[37],"approach":[38],"support":[40],"automatic":[42],"generation":[43],"relationships":[45,82,105],"among":[46,83,107,113],"by":[49,99],"exploiting":[50],"Latent":[51],"Semantic":[52],"Indexing":[53],"(LSI)":[54],"Optical":[56],"Character":[57],"Recognition":[58],"(OCR).":[59],"We":[60],"developed":[61],"LinkDI":[63,87,134,161],"(Linking":[64],"Document":[66],"Images)":[67],"service,":[68],"which":[69,156],"extracts":[70],"indexes":[72],"content,":[75],"computes":[76],"its":[77,95],"latent":[78],"semantics,":[79],"defines":[81],"as":[85,110,112],"hyperlinks.":[86],"was":[88,97],"experimented":[89],"with":[90,165],"performance":[96,132],"evaluated":[98],"comparing":[100],"quality":[102],"created":[106],"textual":[108],"documents":[109],"well":[111],"their":[114],"respective":[115],"images.":[117],"Considering":[118],"those":[119],"same":[120],"images,":[122],"we":[123],"ran":[124],"further":[125],"experiments":[126],"in":[127],"order":[128],"compare":[130],"when":[135],"it":[136],"exploits":[137],"or":[138],"not":[139],"LSI":[141,147],"technique.":[142],"Experimental":[143],"results":[144],"showed":[145],"that":[146],"can":[148],"mitigate":[149],"effects":[151],"usual":[153],"OCR":[154,163],"misrecognition,":[155],"reinforces":[157],"feasibility":[159],"relating":[162],"output":[164],"degradation.":[167]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}
