{"id":"https://openalex.org/W2126220260","doi":"https://doi.org/10.1109/icdim.2007.4444202","title":"Authors’ names extraction from scanned documents","display_name":"Authors’ names extraction from scanned documents","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2126220260","doi":"https://doi.org/10.1109/icdim.2007.4444202","mag":"2126220260"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2007.4444202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","raw_type":"proceedings-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/A5102050481","display_name":"Manabu Ohta","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Manabu Ohta","raw_affiliation_strings":["Okayama University, Okayama, Okayama, Japan"],"affiliations":[{"raw_affiliation_string":"Okayama University, Okayama, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108515735","display_name":"Shun Yamasaki","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shun Yamasaki","raw_affiliation_strings":["Okayama University, Okayama, Okayama, Japan"],"affiliations":[{"raw_affiliation_string":"Okayama University, Okayama, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082401772","display_name":"Takayuki Yakushi","orcid":null},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Yakushi","raw_affiliation_strings":["Okayama University, Okayama, Okayama, Japan"],"affiliations":[{"raw_affiliation_string":"Okayama University, Okayama, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087434029","display_name":"Atsuhiro Takasu","orcid":"https://orcid.org/0000-0002-9061-7949"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiro Takasu","raw_affiliation_strings":["National Institute of Information, Chiyoda, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information, Chiyoda, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102050481"],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":0.9387,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82278371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6202642917633057},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5435178279876709},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5111761689186096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3317773938179016},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32819315791130066},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14054763317108154},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.10702893137931824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6202642917633057},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5435178279876709},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5111761689186096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3317773938179016},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32819315791130066},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14054763317108154},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.10702893137931824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2007.4444202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1487429615","https://openalex.org/W2015432638","https://openalex.org/W2022279359","https://openalex.org/W2043611036","https://openalex.org/W2068613363","https://openalex.org/W2130865917","https://openalex.org/W2135085165","https://openalex.org/W2168190036"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Authors\u2019":[0],"names":[1,53],"are":[2],"a":[3,82,105],"critical":[4],"bibliographic":[5,20],"element":[6],"when":[7],"searching":[8],"or":[9,104],"browsing":[10],"academic":[11,57,114],"articles":[12,58],"stored":[13],"in":[14,95],"digital":[15],"libraries.":[16],"However,":[17],"extracting":[18],"such":[19,39],"data":[21],"from":[22],"printed":[23],"documents":[24],"requires":[25],"human":[26],"intervention;":[27],"it":[28],"is":[29],"therefore":[30],"not":[31],"cost-effective,":[32],"even":[33],"using":[34],"various":[35],"document":[36],"image-processing":[37],"techniques":[38],"as":[40,98],"Optical":[41],"Character":[42],"Recognition":[43],"(OCR).":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"describe":[49],"an":[50,102],"automatic":[51],"authors\u2019":[52,68,131],"extraction":[54],"method":[55,65,111,124],"for":[56,89],"scanned":[59],"with":[60,133],"OCR":[61],"mark-up.":[62],"The":[63],"proposed":[64,110,123,137],"first":[66],"extracts":[67],"blocks,":[69],"which":[70],"include":[71],"assumed":[72],"author/delimiter":[73],"characters":[74],"based":[75],"on":[76],"layout":[77],"analysis,":[78],"and":[79],"then":[80],"uses":[81],"specifically":[83],"designed":[84],"Hidden":[85],"Markov":[86],"Model":[87],"(HMM)":[88],"labeling":[90],"the":[91,96,109,122,136,145],"unsegmented":[92],"character":[93],"strings":[94],"block":[97],"those":[99],"of":[100,117,130,144],"either":[101],"author":[103,146],"delimiter.":[106],"We":[107],"applied":[108],"to":[112],"Japanese":[113],"articles.":[115],"Results":[116],"these":[118],"experiments":[119],"showed":[120],"that":[121],"correctly":[125,139],"extracted":[126],"more":[127,141],"than":[128,142],"99%":[129],"blocks":[132],"manual":[134],"tuning;":[135],"HMM":[138],"labeled":[140],"95%":[143],"name":[147],"strings.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}