{"id":"https://openalex.org/W4229861713","doi":"https://doi.org/10.1109/icpr.2004.1334341","title":"The BBN Byblos Japanese OCR system","display_name":"The BBN Byblos Japanese OCR system","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W4229861713","doi":"https://doi.org/10.1109/icpr.2004.1334341"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2004.1334341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","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/A5044398772","display_name":"Ehry MacRostie","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"E. MacRostie","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Natarajan","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029617574","display_name":"M. Decerbo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Decerbo","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045465417","display_name":"Ramjee Prasad","orcid":"https://orcid.org/0000-0001-7443-7641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Prasad","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044398772"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.296875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"653 Vol.2"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.8296223878860474},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8127292990684509},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.799166202545166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762693166732788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6528796553611755},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6342467069625854},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6071089506149292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5589216351509094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5254706144332886},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47624683380126953},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4375326931476593},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40324002504348755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1060415506362915},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08523967862129211},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06896549463272095}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8296223878860474},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8127292990684509},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.799166202545166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762693166732788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528796553611755},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6342467069625854},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6071089506149292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5589216351509094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5254706144332886},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47624683380126953},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4375326931476593},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40324002504348755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1060415506362915},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08523967862129211},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06896549463272095},{"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":1,"locations":[{"id":"doi:10.1109/icpr.2004.1334341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1984979240","https://openalex.org/W2000528559","https://openalex.org/W2022742307","https://openalex.org/W2050036944","https://openalex.org/W2082183672","https://openalex.org/W6656348407"],"related_works":["https://openalex.org/W1695853225","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W3190162935","https://openalex.org/W2013767392","https://openalex.org/W2026402306","https://openalex.org/W2892857623"],"abstract_inverted_index":{"The":[0,45],"BBN":[1],"Byblos":[2],"OCR":[3,10,59,94],"system":[4,21,35,95,148,183],"implements":[5],"a":[6,74,84,104,121,151,167,191],"script-independent":[7],"methodology":[8],"for":[9,47],"using":[11,83,120,154],"hidden":[12],"Markov":[13],"models":[14],"(HMMs).":[15],"We":[16,28,69,128],"have":[17],"successfully":[18],"ported":[19],"the":[20,34,53,62,71,89,131,145,158,161,182,194],"to":[22,36,143],"Arabic,":[23],"Pashto,":[24],"English,":[25],"and":[26,61,200],"Chinese.":[27],"discuss":[29],"our":[30,48,92],"effort":[31],"in":[32,77,88,113,166],"configuring":[33],"perform":[37],"recognition":[38],"of":[39,55,73,91,124,133,171,178,188],"noisy":[40],"machine":[41],"printed":[42],"Japanese":[43,58,64,116],"documents.":[44],"data":[46],"experimentation":[49],"was":[50,81,118],"taken":[51],"from":[52,157],"University":[54],"Washington":[56],"(UW-II)":[57],"corpus":[60],"LDC":[63],"Business":[65],"News":[66],"Supplement":[67],"corpus.":[68],"evaluated":[70,130],"performance":[72,132],"whole-character":[75,192],"configuration":[76,164,193],"which":[78,114],"each":[79,115],"character":[80,117,168],"modeled":[82],"separate":[85],"HMM.":[86],"As":[87],"case":[90],"Chinese":[93],"[P.":[96,108],"Natarajan":[97,109],"et":[98,110],"al.,":[99,111],"2001],":[100],"we":[101],"also":[102],"used":[103],"sub-character":[105,135,163],"modeling":[106],"approach":[107],"2003]":[112],"spelled":[119],"shared":[122],"set":[123],"automatically":[125],"generated":[126],"sub-characters.":[127],"experimentally":[129],"different":[134,140],"clusters":[136],"as":[137,139],"well":[138],"HMM":[141],"topologies":[142],"identify":[144],"best":[146,162],"overall":[147],"configuration.":[149],"On":[150,173],"fair":[152],"test":[153],"noisy/degraded":[155],"images":[156],"UW-II":[159],"corpus,":[160],"resulted":[165],"error":[169,186,196],"rate":[170,187],"20.13%,":[172],"relatively":[174],"cleaner":[175],"data,":[176],"consisting":[177],"scanned":[179],"newspaper":[180],"images,":[181],"delivered":[184],"an":[185],"7.85%.":[189],"Using":[190],"corresponding":[195],"rates":[197],"were":[198],"11.94%":[199],"4.55%":[201],"respectively.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}