{"id":"https://openalex.org/W2044030350","doi":"https://doi.org/10.1109/cvpr.2010.5539867","title":"Improving state-of-the-art OCR through high-precision document-specific modeling","display_name":"Improving state-of-the-art OCR through high-precision document-specific modeling","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2044030350","doi":"https://doi.org/10.1109/cvpr.2010.5539867","mag":"2044030350"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2010.5539867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5539867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/erik_learned_miller/56/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012575423","display_name":"Andrew Kae","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Kae","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, USA","[Department of Computer Science, University of Massachusetts, Amherst]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"[Department of Computer Science, University of Massachusetts, Amherst]","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087287079","display_name":"Gary B. Huang","orcid":"https://orcid.org/0000-0002-9606-3510"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Huang","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, USA","[Department of Computer Science, University of Massachusetts, Amherst]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"[Department of Computer Science, University of Massachusetts, Amherst]","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081047759","display_name":"Carl Doersch","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Doersch","raw_affiliation_strings":["Department of Computer Science, Carnegie Mellon University, USA","Department of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045674062","display_name":"Erik Learned-Miller","orcid":"https://orcid.org/0000-0002-3778-9135"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Learned-Miller","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, USA","[Department of Computer Science, University of Massachusetts, Amherst]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"[Department of Computer Science, University of Massachusetts, Amherst]","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"1935","last_page":"1942"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.8498703837394714},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7450631856918335},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.6852301359176636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6579147577285767},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6163020730018616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6113860607147217},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5586820840835571},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5278263688087463},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4643905758857727},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4613625407218933},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4023987650871277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.391300767660141},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38608241081237793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2018757462501526},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10484415292739868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498703837394714},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7450631856918335},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.6852301359176636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6579147577285767},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6163020730018616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6113860607147217},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5586820840835571},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5278263688087463},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4643905758857727},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4613625407218933},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4023987650871277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.391300767660141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38608241081237793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2018757462501526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10484415292739868},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2010.5539867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2010.5539867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:erik_learned_miller-1111","is_oa":true,"landing_page_url":"https://works.bepress.com/erik_learned_miller/56","pdf_url":"https://works.bepress.com/erik_learned_miller/56/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Erik G Learned-Miller","raw_type":"text"},{"id":"pmh:oai:works.bepress.com:andrew_kae-1002","is_oa":false,"landing_page_url":"https://works.bepress.com/andrew_kae/3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew Kae","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:erik_learned_miller-1111","is_oa":true,"landing_page_url":"https://works.bepress.com/erik_learned_miller/56","pdf_url":"https://works.bepress.com/erik_learned_miller/56/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Erik G Learned-Miller","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2044030350.pdf","grobid_xml":"https://content.openalex.org/works/W2044030350.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1515641296","https://openalex.org/W2010595692","https://openalex.org/W2045566081","https://openalex.org/W2081366726","https://openalex.org/W2112890726","https://openalex.org/W2114781615","https://openalex.org/W2124007105","https://openalex.org/W2126086996","https://openalex.org/W2141756865","https://openalex.org/W2141960239","https://openalex.org/W2144166648","https://openalex.org/W2144839447","https://openalex.org/W2151103935","https://openalex.org/W2158902672","https://openalex.org/W2429914308","https://openalex.org/W2949648941","https://openalex.org/W6630732937","https://openalex.org/W6676809873","https://openalex.org/W6678817347","https://openalex.org/W6681335746","https://openalex.org/W6681602672"],"related_works":["https://openalex.org/W2147687867","https://openalex.org/W2582695981","https://openalex.org/W2496907786","https://openalex.org/W2483185727","https://openalex.org/W2612325988","https://openalex.org/W2490611030","https://openalex.org/W3022607756","https://openalex.org/W2043030904","https://openalex.org/W2327192489","https://openalex.org/W2487016776"],"abstract_inverted_index":{"Optical":[0],"character":[1,54,100,145,204],"recognition":[2],"(OCR)":[3],"remains":[4],"a":[5,41,88,125,152,169,197],"difficult":[6,173],"problem":[7],"for":[8,91],"noisy":[9,36],"documents":[10,12],"or":[11,37],"not":[13],"scanned":[14],"at":[15],"high":[16,132],"resolution.":[17],"Many":[18],"current":[19],"approaches":[20],"rely":[21],"on":[22,168],"stored":[23,46],"font":[24,42,65],"models":[25,55,102,205],"that":[26,129,151,178],"are":[27,78,211],"vulnerable":[28],"to":[29,44,80,116,142,161,195,213],"cases":[30],"in":[31,40,73,84,154,184,193],"which":[32],"the":[33,45,58,74,111,155,190,215,225],"document":[34,59],"is":[35,38,158],"written":[39],"dissimilar":[43],"fonts.":[47],"We":[48,147,187],"address":[49],"these":[50],"problems":[51],"by":[52,221],"learning":[53],"directly":[56],"from":[57,103,207,224],"itself,":[60],"rather":[61],"than":[62],"using":[63,202],"pre-stored":[64],"models.":[66,146],"This":[67],"method":[68,90,123],"has":[69],"had":[70],"some":[71],"success":[72],"past,":[75],"but":[76],"we":[77,108,130,179,210],"able":[79,212],"achieve":[81],"substantial":[82],"improvement":[83],"error":[85,216],"reduction":[86],"through":[87],"novel":[89],"creating":[92],"nearly":[93],"error-free":[94],"document-specific":[95,144,203],"training":[96,199],"data":[97,170],"and":[98,138,165,201],"building":[99],"appearance":[101],"this":[104,140,208],"data.":[105],"In":[106],"particular,":[107],"first":[109],"use":[110],"state-of-the-art":[112],"OCR":[113],"system":[114],"Tesseract":[115,227],"produce":[117],"an":[118],"initial":[119,226],"translation.":[120,228],"Then,":[121],"our":[122],"identifies":[124],"subset":[126,141,157],"of":[127,172],"words":[128],"have":[131,134],"confidence":[133],"been":[135],"recognized":[136],"correctly":[137],"uses":[139],"bootstrap":[143],"present":[148],"theoretical":[149,191],"justification":[150],"word":[153],"selected":[156],"very":[159],"unlikely":[160],"be":[162],"incorrectly":[163],"recognized,":[164],"empirical":[166],"results":[167],"set":[171],"historical":[174],"newspaper":[175],"scans":[176],"demonstrating":[177],"make":[180],"only":[181],"two":[182],"errors":[183],"56":[185],"documents.":[186],"then":[188],"relax":[189],"constraint":[192],"order":[194],"create":[196],"larger":[198],"set,":[200],"generated":[206],"data,":[209],"reduce":[214],"over":[217],"properly":[218],"segmented":[219],"characters":[220],"34.1%":[222],"overall":[223]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}