{"id":"https://openalex.org/W2140339170","doi":"https://doi.org/10.1145/1378889.1378918","title":"A metadata generation system for scanned scientific volumes","display_name":"A metadata generation system for scanned scientific volumes","publication_year":2008,"publication_date":"2008-06-16","ids":{"openalex":"https://openalex.org/W2140339170","doi":"https://doi.org/10.1145/1378889.1378918","mag":"2140339170"},"language":"en","primary_location":{"id":"doi:10.1145/1378889.1378918","doi":"https://doi.org/10.1145/1378889.1378918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378889.1378918","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5065336897","display_name":"Xiaonan L\u00fc","orcid":"https://orcid.org/0000-0003-4294-6673","observed_orcids":["https://orcid.org/0000-0003-4294-6673"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Lu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111886096","display_name":"Brewster Kahle","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210124753","display_name":"Internet Archive","ror":"https://ror.org/02z468g17","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210124753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brewster Kahle","raw_affiliation_strings":["Internet Archive, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Internet Archive, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210124753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687159","display_name":"James Z. Wang","orcid":"https://orcid.org/0000-0003-4379-4173","observed_orcids":["https://orcid.org/0000-0003-4379-4173","https://orcid.org/0009-0009-1205-9492"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Z. Wang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"Clyde Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X","observed_orcids":["https://orcid.org/0000-0002-1931-585X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4654,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94576903,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.3449999988079071,"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":0.3449999988079071,"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/T14330","display_name":"Library Science and Information Systems","score":0.2985999882221222,"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"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.14550000429153442,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata-extraction","display_name":"metadata extraction","score":0.777999997138977},{"id":"https://openalex.org/keywords/digitized-books","display_name":"digitized books","score":0.5820000171661377},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.8309999704360962},{"id":"https://openalex.org/keywords/article-level-metadata","display_name":"article-level metadata","score":0.9959999918937683},{"id":"https://openalex.org/keywords/historical-documents","display_name":"historical documents","score":0.7739999890327454},{"id":"https://openalex.org/keywords/digital-libraries","display_name":"digital libraries","score":0.7149999737739563},{"id":"https://openalex.org/keywords/internet-archive","display_name":"Internet Archive","score":0.8610000014305115},{"id":"https://openalex.org/keywords/textual-features","display_name":"text features","score":0.5260000228881836}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9275270104408264},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.894715428352356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345827460289001},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6502965688705444},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5690178871154785},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5594903230667114},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5261654257774353},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5026857852935791},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45522579550743103},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3476569354534149},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3216443359851837},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0726877748966217},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1378889.1378918","doi":"https://doi.org/10.1145/1378889.1378918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378889.1378918","pdf_url":null,"source":{"id":"https://openalex.org/S4306417562","display_name":"ACM/IEEE Joint Conference on Digital Libraries","issn_l":"1552-5996","issn":["1552-5996"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.3525","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.3525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clgiles.ist.psu.edu/papers/JCDL2008-metadata-generation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.3699","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.3699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.psu.edu/~xlu/publications/jcdl08-lu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306083","display_name":"Smithsonian Institution","ror":"https://ror.org/01pp8nd67"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W1528781420","https://openalex.org/W1576520375","https://openalex.org/W1604938182","https://openalex.org/W1647671624","https://openalex.org/W1941659294","https://openalex.org/W1998839545","https://openalex.org/W2051192072","https://openalex.org/W2054567126","https://openalex.org/W2099105514","https://openalex.org/W2113410090","https://openalex.org/W2124303864","https://openalex.org/W2145657314","https://openalex.org/W2160442351","https://openalex.org/W2168190036","https://openalex.org/W3151004646","https://openalex.org/W4238290165","https://openalex.org/W4253723135"],"related_works":["https://openalex.org/W7096002164","https://openalex.org/W2102358834","https://openalex.org/W2540481080","https://openalex.org/W7098701606","https://openalex.org/W2315226865","https://openalex.org/W7098298725","https://openalex.org/W7101102768","https://openalex.org/W7096065301","https://openalex.org/W3216056955","https://openalex.org/W7048556414"],"abstract_inverted_index":{"Large":[0],"scale":[1],"digitization":[2],"projects":[3],"have":[4,131],"been":[5],"conducted":[6],"at":[7],"digital":[8,87,141],"libraries":[9],"to":[10,15,66,86],"preserve":[11],"cultural":[12],"artifacts":[13],"and":[14,28,35,41,72,100,107,135],"provide":[16],"permanent":[17],"access.":[18],"The":[19],"increasing":[20],"amount":[21],"of":[22,33,45,55,61,74,118],"digitized":[23,46],"resources,":[24],"including":[25],"scanned":[26,59,75,122],"books":[27],"scientific":[29],"publications,":[30],"requires":[31],"development":[32],"tools":[34],"methods":[36,92],"that":[37],"will":[38],"efficiently":[39],"analyze":[40],"manage":[42],"large":[43],"collections":[44],"resources.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"tackle":[52],"the":[53,116,133,143],"problem":[54],"extracting":[56],"metadata":[57,103],"from":[58,111],"volumes":[60],"journals.":[62],"Our":[63],"goal":[64],"is":[65,78],"extract":[67],"information":[68],"describing":[69],"internal":[70],"structures":[71],"content":[73,83],"volumes,":[76],"which":[77],"necessary":[79],"for":[80,93,146],"providing":[81],"effective":[82],"access":[84],"functionalities":[85],"library":[88],"users.":[89],"We":[90,114,130],"propose":[91],"automatically":[94],"generating":[95],"volume":[96],"level,":[97,99],"issue":[98],"article":[101],"level":[102],"based":[104],"on":[105,121],"format":[106],"text":[108],"features":[109],"extracted":[110],"OCRed":[112],"text.":[113],"show":[115],"performance":[117],"our":[119],"system":[120,134],"bound":[123],"historical":[124],"documents":[125],"nearly":[126],"two":[127],"centuries":[128],"old.":[129],"developed":[132],"integrated":[136],"it":[137],"into":[138],"an":[139],"operational":[140],"library,":[142],"Internet":[144],"Archive,":[145],"real-world":[147],"usage.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
