{"id":"https://openalex.org/W2124303864","doi":"https://doi.org/10.1109/dial.2004.1263251","title":"A dynamic feature generation system for automated metadata extraction in preservation of digital materials","display_name":"A dynamic feature generation system for automated metadata extraction in preservation of digital materials","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2124303864","doi":"https://doi.org/10.1109/dial.2004.1263251","mag":"2124303864"},"language":"en","primary_location":{"id":"doi:10.1109/dial.2004.1263251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","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/A5008633788","display_name":"Song Mao","orcid":"https://orcid.org/0000-0001-7851-6347"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Mao","raw_affiliation_strings":["National Library of Medicine, Bethesda, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Bethesda, MD, USA","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385616","display_name":"Jong Woo Kim","orcid":"https://orcid.org/0000-0001-9484-5968"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Woo Kim","raw_affiliation_strings":["National Library of Medicine, Bethesda, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Bethesda, MD, USA","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074891005","display_name":"Grid Thoma","orcid":"https://orcid.org/0000-0001-9836-2605"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.R. Thoma","raw_affiliation_strings":["National Library of Medicine, Bethesda, MD, USA","Nat. Libr. of Med., Bethesda, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Bethesda, MD, USA","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"Nat. Libr. of Med., Bethesda, MD, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.315,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92846622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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/T10601","display_name":"Handwritten Text Recognition 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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9987000226974487,"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":0.9983999729156494,"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":0.9152297377586365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8316166996955872},{"id":"https://openalex.org/keywords/obsolescence","display_name":"Obsolescence","score":0.8248766660690308},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6422401070594788},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5827630758285522},{"id":"https://openalex.org/keywords/digital-preservation","display_name":"Digital preservation","score":0.5264697074890137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5247321724891663},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5150899291038513},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5090076923370361},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.49058952927589417},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44472986459732056},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.41833069920539856},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.41689354181289673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37976694107055664},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33716902136802673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2549922466278076},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0912037193775177}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9152297377586365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8316166996955872},{"id":"https://openalex.org/C30795975","wikidata":"https://www.wikidata.org/wiki/Q282744","display_name":"Obsolescence","level":2,"score":0.8248766660690308},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6422401070594788},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5827630758285522},{"id":"https://openalex.org/C2778674798","wikidata":"https://www.wikidata.org/wiki/Q632897","display_name":"Digital preservation","level":2,"score":0.5264697074890137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5247321724891663},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5150899291038513},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5090076923370361},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.49058952927589417},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44472986459732056},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41833069920539856},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.41689354181289673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37976694107055664},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33716902136802673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2549922466278076},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0912037193775177},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dial.2004.1263251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1970026646","https://openalex.org/W1970516708","https://openalex.org/W1994471599","https://openalex.org/W1995035417"],"related_works":["https://openalex.org/W2021123232","https://openalex.org/W1552553528","https://openalex.org/W2097146382","https://openalex.org/W2745365209","https://openalex.org/W2183628870","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2782431616","https://openalex.org/W2394393789","https://openalex.org/W2374379029"],"abstract_inverted_index":{"Obsolescence":[0],"in":[1,203],"storage":[2],"media":[3],"and":[4,7,11,19,50,89,119,134],"the":[5,22,36,46,75,83,171,177,205,236,244],"hardware":[6],"software":[8],"for":[9,208],"access":[10],"use":[12],"can":[13,226],"render":[14],"old":[15],"electronic":[16],"files":[17],"inaccessible":[18],"unusable.":[20],"Therefore,":[21],"long-term":[23],"preservation":[24,47],"of":[25,33,40,48,64,67,86,93,140,142,159,173,183,235],"digital":[26,80],"materials":[27],"has":[28,104],"become":[29],"an":[30],"active":[31],"area":[32],"research.":[34],"At":[35],"U.S.":[37],"National":[38],"Library":[39],"Medicine":[41],"(NLM),":[42],"we":[43],"are":[44,62,166,214],"investigating":[45],"scanned":[49,122],"online":[51],"medical":[52,87,123],"journal":[53,160,184,212],"articles,":[54],"though":[55],"other":[56],"data":[57,95],"types":[58,69],"(e.g.,":[59],"video":[60],"sequences)":[61],"also":[63],"interest.":[65],"Metadata":[66],"different":[68,194,233],"have":[70],"been":[71,105],"proposed":[72],"to":[73,78,109,131,155,191,228],"save":[74],"information":[76],"needed":[77],"preserve":[79],"materials.":[81],"Given":[82],"ever-increasing":[84],"volume":[85],"journals":[88],"high":[90],"labor":[91],"cost":[92],"manual":[94],"entry,":[96],"automated":[97],"metadata":[98,113],"extraction":[99],"is":[100,129],"crucial.":[101],"A":[102,125,145],"system":[103,202,225,246],"developed":[106],"at":[107],"NLM":[108],"automatically":[110],"generate":[111,132],"descriptive":[112],"that":[114,243],"includes":[115],"title,":[116],"author,":[117],"affiliation,":[118],"abstract":[120],"from":[121,137,180,216],"journals.":[124],"module":[126,148],"called":[127],"ZoneMatch":[128],"used":[130,207],"geometric":[133],"contextual":[135],"features":[136,154,178,206],"a":[138,174,193,198,210],"set":[139,182],"issues":[141,172,185,218,234],"each":[143],"journal.":[144,238],"rule-based":[146],"labeling":[147,157,209,249],"(called":[149],"ZoneCzar)":[150],"then":[151],"uses":[152],"these":[153],"perform":[156],"independent":[158],"layout":[161,221],"styles.":[162],"However,":[163],"if":[164],"there":[165],"significant":[167],"style":[168,230],"variations":[169,231],"among":[170,232],"same":[175,237],"journal,":[176],"generated":[179,215],"one":[181],"may":[186],"not":[187],"be":[188],"very":[189],"useful":[190],"label":[192],"set.":[195],"We":[196],"describe":[197],"dynamic":[199],"feature":[200],"updating":[201],"which":[204],"current":[211],"issue":[213],"previous":[217],"with":[219],"similar":[220],"style.":[222],"This":[223],"new":[224,245],"adapt":[227],"possible":[229],"Experimental":[239],"results":[240],"presented":[241],"show":[242],"delivers":[247],"improved":[248],"performance":[250],"accuracy.":[251]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"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":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}