{"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","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378889.1378918","pdf_url":null,"source":null,"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"},"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/A5065336897","display_name":"Xiaonan L\u00fc","orcid":"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":true,"raw_author_name":"Xiaonan Lu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"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},"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"],"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"},"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","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"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":"C. Lee Giles","orcid":"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","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5065336897"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":46.8953,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.99669057,"is_in_top_1_percent":true,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9962999820709229,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.994700014591217,"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/metadata","display_name":"Metadata","score":0.9275270104408264},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.894715428352356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345827460289001},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6502965688705444},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5690178871154785},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5594903230667114},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5261654257774353},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5026857852935791},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45522579550743103},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3476569354534149},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3216443359851837},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0726877748966217}],"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","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378889.1378918","pdf_url":null,"source":null,"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","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","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"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/W2140479099","https://openalex.org/W2145657314","https://openalex.org/W2160442351","https://openalex.org/W2168190036","https://openalex.org/W2610260431","https://openalex.org/W3151004646","https://openalex.org/W4238290165","https://openalex.org/W6634442568","https://openalex.org/W6640479084"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4251369848","https://openalex.org/W1987401411","https://openalex.org/W2746392713","https://openalex.org/W2163748916","https://openalex.org/W3167700301","https://openalex.org/W2002966468","https://openalex.org/W2368778223"],"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":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
