{"id":"https://openalex.org/W2171663110","doi":"https://doi.org/10.1109/dial.2004.1263245","title":"Document style census for OCR","display_name":"Document style census for OCR","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2171663110","doi":"https://doi.org/10.1109/dial.2004.1263245","mag":"2171663110"},"language":"en","primary_location":{"id":"doi:10.1109/dial.2004.1263245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263245","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/A5015992700","display_name":"George Nagy","orcid":"https://orcid.org/0000-0002-0521-1443"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Nagy","raw_affiliation_strings":["DocLaboratory, Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DocLaboratory, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109222302","display_name":"P. Sarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sarkar","raw_affiliation_strings":["Palo Alto Research Center, Inc.orporated, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Palo Alto Research Center, Inc.orporated, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5525,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71722627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3584","issue":null,"first_page":"134","last_page":"147"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9952999949455261,"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/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/optical-character-recognition","display_name":"Optical character recognition","score":0.7483471035957336},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7288440465927124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282776832580566},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5558453798294067},{"id":"https://openalex.org/keywords/homogeneity","display_name":"Homogeneity (statistics)","score":0.4558206796646118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43900197744369507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42655646800994873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3964233994483948},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35865092277526855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2780214548110962},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08704563975334167}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7483471035957336},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7288440465927124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282776832580566},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5558453798294067},{"id":"https://openalex.org/C142259097","wikidata":"https://www.wikidata.org/wiki/Q5891314","display_name":"Homogeneity (statistics)","level":2,"score":0.4558206796646118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43900197744369507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42655646800994873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3964233994483948},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35865092277526855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2780214548110962},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08704563975334167},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dial.2004.1263245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263245","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.202.7713","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.202.7713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ecse.rpi.edu/homepages/nagy/PDF_files/DIAL04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W27981834","https://openalex.org/W124367838","https://openalex.org/W128810854","https://openalex.org/W1512487361","https://openalex.org/W1768731754","https://openalex.org/W1977561118","https://openalex.org/W1980079039","https://openalex.org/W1985708392","https://openalex.org/W1986282506","https://openalex.org/W1991691398","https://openalex.org/W2005446794","https://openalex.org/W2097089247","https://openalex.org/W2097346260","https://openalex.org/W2101358131","https://openalex.org/W2102734279","https://openalex.org/W2104439255","https://openalex.org/W2104791794","https://openalex.org/W2113723031","https://openalex.org/W2114678998","https://openalex.org/W2116382902","https://openalex.org/W2117120770","https://openalex.org/W2123304600","https://openalex.org/W2124007105","https://openalex.org/W2125389487","https://openalex.org/W2127148691","https://openalex.org/W2141475220","https://openalex.org/W2152114086","https://openalex.org/W2158052399","https://openalex.org/W2160244865","https://openalex.org/W2161074727","https://openalex.org/W2169541759","https://openalex.org/W2315761891","https://openalex.org/W6605244207","https://openalex.org/W6644816899","https://openalex.org/W6651805505","https://openalex.org/W6675608222"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W3190162935","https://openalex.org/W2013767392","https://openalex.org/W2892857623","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2595338207"],"abstract_inverted_index":{"Four":[0],"methods":[1],"of":[2,38,51,66,89],"converting":[3],"paper":[4],"documents":[5],"to":[6,13,71],"computer-readable":[7],"form":[8],"are":[9,78],"compared":[10],"with":[11],"regard":[12],"hypothetical":[14],"labor":[15],"cost:":[16],"keyboarding,":[17],"omnifont":[18],"OCR,":[19,21],"style-specific":[20],"and":[22,62,85],"style-constrained":[23],"or":[24],"style-adaptive":[25],"OCR.":[26],"The":[27],"best":[28],"choice":[29],"is":[30],"determined":[31],"primarily":[32],"by":[33],"(1)":[34],"the":[35,39,49,52,60,64,68],"reject":[36],"rates":[37],"various":[40],"OCR":[41],"systems":[42],"at":[43],"a":[44],"given":[45],"error":[46],"rate,":[47],"(2)":[48],"fraction":[50],"material":[53,69],"that":[54],"must":[55],"be":[56],"labeled":[57],"for":[58,81,86],"training":[59],"system,":[61],"(3)":[63],"cost":[65],"partitioning":[67],"according":[70],"style.":[72],"For":[73],"large":[74],"corpora,":[75],"sampling":[76],"strategies":[77],"proposed":[79],"both":[80],"estimating":[82],"conversion":[83],"costs":[84],"taking":[87],"advantage":[88],"style":[90],"homogeneity.":[91]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}