{"id":"https://openalex.org/W2003553779","doi":"https://doi.org/10.1109/escience.2012.6404445","title":"Digitization and search: A non-traditional use of HPC","display_name":"Digitization and search: A non-traditional use of HPC","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2003553779","doi":"https://doi.org/10.1109/escience.2012.6404445","mag":"2003553779"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2012.6404445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2012.6404445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 8th International Conference on E-Science","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/A5089546440","display_name":"Liana Diesendruck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liana Diesendruck","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034386740","display_name":"Luigi Marini","orcid":"https://orcid.org/0000-0002-8511-0211"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luigi Marini","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025183449","display_name":"Rob Kooper","orcid":"https://orcid.org/0000-0002-5781-7287"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Kooper","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074197492","display_name":"Mayank Kejriwal","orcid":"https://orcid.org/0000-0001-5988-8305"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Kejriwal","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059328010","display_name":"Kenton McHenry","orcid":"https://orcid.org/0000-0003-0367-2550"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenton McHenry","raw_affiliation_strings":["National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications University of Illinois at Urbana-Champaign,","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089546440"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"],"apc_list":null,"apc_paid":null,"fwci":0.5551,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67304866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9973999857902527,"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":0.9950000047683716,"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/digitization","display_name":"Digitization","score":0.8578375577926636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8485169410705566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6090237498283386},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5450400114059448},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.4951843321323395},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43305474519729614},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43074285984039307},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4195733964443207},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41778475046157837},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41026195883750916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25362712144851685}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.8578375577926636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485169410705566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6090237498283386},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5450400114059448},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.4951843321323395},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43305474519729614},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43074285984039307},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4195733964443207},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41778475046157837},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41026195883750916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25362712144851685},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/escience.2012.6404445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2012.6404445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 8th International Conference on E-Science","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.670.3115","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.670.3115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isda.ncsa.illinois.edu/drupal/sites/default/files/escience_workshop.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.1199","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.1199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://isda.ncsa.illinois.edu/drupal/sites/default/files/SC12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1543768931","https://openalex.org/W1932188282","https://openalex.org/W2000782346","https://openalex.org/W2003213232","https://openalex.org/W2024077020","https://openalex.org/W2035890032","https://openalex.org/W2060746081","https://openalex.org/W2095905764","https://openalex.org/W2112489058","https://openalex.org/W2122141098","https://openalex.org/W2134097102","https://openalex.org/W2135249422","https://openalex.org/W2142069714","https://openalex.org/W2153166546","https://openalex.org/W2162838084","https://openalex.org/W2167929403"],"related_works":["https://openalex.org/W629813691","https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W2592115649","https://openalex.org/W4322582183","https://openalex.org/W1937392525"],"abstract_inverted_index":{"Automated":[0],"search":[1,128],"of":[2,20,55,89,94,100,112,121,172,186,216],"handwritten":[3,60,90],"content":[4,70],"is":[5,84,115],"a":[6,62,69,214],"highly":[7],"interesting":[8],"and":[9,43,97,138],"applicative":[10],"subject,":[11],"especially":[12],"important":[13],"today":[14],"due":[15],"to":[16,34,38,49,57,106,117,125,156,160,195,205,209],"the":[17,30,39,45,51,59,82,87,107,119,122,139,165,170,176,184,187],"public":[18],"availability":[19],"large":[21],"digitized":[22,217],"document":[23],"collections.":[24],"We":[25],"describe":[26],"our":[27],"efforts":[28],"with":[29],"National":[31],"Archives":[32],"(NARA)":[33],"provide":[35,157,206],"searchable":[36,158],"access":[37,159],"1940":[40,191],"Census":[41,178],"data":[42,123],"discuss":[44],"HPC":[46,149],"resources":[47],"needed":[48,116],"implement":[50],"suggested":[52],"framework.":[53],"Instead":[54],"trying":[56],"recognize":[58],"text,":[61],"still":[63],"very":[64],"difficult":[65],"task,":[66],"we":[67,182],"use":[68,88],"based":[71],"image":[72],"retrieval":[73],"technique":[74],"known":[75],"as":[76,164],"Word":[77],"Spotting.":[78],"Through":[79],"this":[80,127],"paradigm,":[81],"system":[83],"queried":[85],"by":[86],"text":[91,96],"images":[92,103],"instead":[93],"ASCII":[95],"ranked":[98],"groups":[99],"similar":[101],"looking":[102],"are":[104,144,152],"presented":[105],"user.":[108],"A":[109],"significant":[110],"amount":[111],"computing":[113],"power":[114],"accomplish":[118],"pre-processing":[120],"so":[124],"make":[126],"capability":[129],"available":[130],"on":[131,148],"an":[132,207],"archive.":[133],"The":[134,199],"required":[135],"preprocessing":[136],"steps":[137],"open":[140],"source":[141],"framework":[142,201],"developed":[143],"discussed":[145],"focusing":[146],"specifically":[147],"considerations":[150],"that":[151],"relevant":[153],"when":[154],"preparing":[155],"sizeable":[161],"collections,":[162],"such":[163],"US":[166],"Census.":[167],"Having":[168],"processed":[169],"state":[171],"North":[173],"Carolina":[174],"from":[175],"1930":[177],"using":[179],"98,000":[180],"SUs":[181],"estimate":[183],"processing":[185],"entire":[188],"country":[189],"for":[190,213],"could":[192],"require":[193],"up":[194],"2.5":[196],"million":[197],"SUs.":[198],"proposed":[200],"can":[202],"be":[203],"used":[204],"alternative":[208],"costly":[210],"manual":[211],"transcriptions":[212],"variety":[215],"paper":[218],"archives.":[219]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
