{"id":"https://openalex.org/W2100290014","doi":"https://doi.org/10.1109/icdim.2008.4746745","title":"Bibliographic element extraction from scanned documents using conditional random fields","display_name":"Bibliographic element extraction from scanned documents using conditional random fields","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2100290014","doi":"https://doi.org/10.1109/icdim.2008.4746745","mag":"2100290014"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third 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/I136446963","display_name":"Okayama University of Science","ror":"https://ror.org/05aevyc10","country_code":"JP","type":"education","lineage":["https://openalex.org/I136446963"]},{"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 of Science, Okayama, Japan","Okayama Univ., Okayama"],"affiliations":[{"raw_affiliation_string":"Okayama University of Science, Okayama, Japan","institution_ids":["https://openalex.org/I136446963"]},{"raw_affiliation_string":"Okayama Univ., Okayama","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"]},{"id":"https://openalex.org/I136446963","display_name":"Okayama University of Science","ror":"https://ror.org/05aevyc10","country_code":"JP","type":"education","lineage":["https://openalex.org/I136446963"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Yakushi","raw_affiliation_strings":["Okayama University of Science, Okayama, Japan","Okayama Univ., Okayama"],"affiliations":[{"raw_affiliation_string":"Okayama University of Science, Okayama, Japan","institution_ids":["https://openalex.org/I136446963"]},{"raw_affiliation_string":"Okayama Univ., Okayama","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, Tokyo, Japan","Nat. Inst. of Inf., Tokyo"],"affiliations":[{"raw_affiliation_string":"National Institute of Information, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Nat. Inst. of Inf., Tokyo","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102050481"],"corresponding_institution_ids":["https://openalex.org/I136446963","https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":1.0536,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79559153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"104"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9869999885559082,"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/conditional-random-field","display_name":"Conditional random field","score":0.8070657849311829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8066756725311279},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.7264038324356079},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.712134838104248},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6537866592407227},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6010201573371887},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5419278144836426},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.5377445816993713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867522716522217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4771101772785187},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42736196517944336},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.41676419973373413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3436241149902344},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.19039568305015564},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18147870898246765},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07921433448791504}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8070657849311829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066756725311279},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.7264038324356079},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.712134838104248},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6537866592407227},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6010201573371887},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5419278144836426},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.5377445816993713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867522716522217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4771101772785187},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42736196517944336},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.41676419973373413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3436241149902344},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.19039568305015564},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18147870898246765},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07921433448791504},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2008.4746745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W165283731","https://openalex.org/W2015432638","https://openalex.org/W2043611036","https://openalex.org/W2048003264","https://openalex.org/W2068613363","https://openalex.org/W2130865917","https://openalex.org/W2135085165","https://openalex.org/W2147880316","https://openalex.org/W2171409580","https://openalex.org/W2252264945","https://openalex.org/W6606787761","https://openalex.org/W6682082992","https://openalex.org/W6685286131","https://openalex.org/W6691657211"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W4388119604","https://openalex.org/W2078296418","https://openalex.org/W1492005981","https://openalex.org/W1982302668","https://openalex.org/W3015234152"],"abstract_inverted_index":{"Bibliographic":[0],"databases":[1],"are":[2],"indispensable":[3],"to":[4,87,118],"digital":[5],"libraries":[6],"for":[7,51,104],"academic":[8,52,120],"articles.":[9,121],"However,":[10],"extracting":[11],"bibliographic":[12,47,67,136],"elements":[13,68,137],"from":[14,92,138,157],"printed":[15],"documents":[16],"requires":[17],"a":[18],"lot":[19],"of":[20,142,161],"human":[21],"intervention;":[22],"it":[23],"is":[24],"not":[25],"cost-effective,":[26],"even":[27],"when":[28],"using":[29],"various":[30],"document":[31],"image-processing":[32],"techniques":[33],"such":[34],"as":[35,65],"optical":[36],"character":[37,147],"recognition":[38],"(OCR).":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"an":[45],"automatic":[46],"element":[48],"extraction":[49],"method":[50,60,98,117],"articles":[53],"scanned":[54],"with":[55],"OCR":[56],"markup.":[57],"The":[58,82,97,122],"proposed":[59,127,146],"first":[61],"labels":[62,72],"text":[63,78,95,107,128,164],"blocks":[64,108,165],"predetermined":[66],"and":[69,109],"then":[70],"further":[71],"the":[73,93,110,116,126,134,143,145,153,162],"characters":[74,111],"in":[75,112,166],"each":[76,89],"labeled":[77],"block":[79,129],"if":[80],"necessary.":[81],"second":[83],"labeling":[84,105,130,148],"enables":[85],"us":[86],"extract":[88],"authorpsilas":[90],"name":[91,155],"authorspsila":[94,163],"block.":[96],"uses":[99],"conditional":[100],"random":[101],"fields":[102],"(CRF)":[103],"both":[106],"them.":[113],"We":[114],"applied":[115],"Japanese":[119],"experiments":[123],"showed":[124],"that":[125],"correctly":[131,150],"extracted":[132,151],"all":[133,152],"predefined":[135],"more":[139,158],"than":[140,159],"97%":[141],"articles;":[144],"also":[149],"author":[154],"strings":[156],"99%":[160],"Japanese.":[167]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}