{"id":"https://openalex.org/W2077916012","doi":"https://doi.org/10.1109/icdar.2007.4377043","title":"A Weighted Finite-State Framework for Correcting Errors in Natural Scene OCR","display_name":"A Weighted Finite-State Framework for Correcting Errors in Natural Scene OCR","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2077916012","doi":"https://doi.org/10.1109/icdar.2007.4377043","mag":"2077916012"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377043","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080012604","display_name":"Richard Beaufort","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143459","display_name":"Multitel","ror":"https://ror.org/042e7c302","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210143459"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"R. Beaufort","raw_affiliation_strings":["Multitel Research Center, Belgium","Multitel Res. Center, Mons"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multitel Research Center, Belgium","institution_ids":["https://openalex.org/I4210143459"]},{"raw_affiliation_string":"Multitel Res. Center, Mons","institution_ids":["https://openalex.org/I4210143459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002991473","display_name":"C\u00e9line Mancas-Thillou","orcid":null},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"C. Mancas-Thillou","raw_affiliation_strings":["Facult\u00e9 Polytechnique de Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facult\u00e9 Polytechnique de Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0512,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.75029546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"889","last_page":"893"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944000244140625,"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":0.7978144884109497},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6686733961105347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6388528943061829},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6255613565444946},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5968565940856934},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5754910707473755},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5683524012565613},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5590206384658813},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5474082827568054},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5400515198707581},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48794859647750854},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4360741376876831},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.42938846349716187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42212679982185364},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.41120022535324097},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1599251627922058},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14982560276985168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978144884109497},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6686733961105347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6388528943061829},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6255613565444946},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5968565940856934},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5754910707473755},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5683524012565613},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5590206384658813},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5474082827568054},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5400515198707581},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48794859647750854},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4360741376876831},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.42938846349716187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42212679982185364},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.41120022535324097},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1599251627922058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14982560276985168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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":2,"locations":[{"id":"doi:10.1109/icdar.2007.4377043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377043","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/41275","is_oa":false,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/41275","pdf_url":null,"source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"9th International Conference on Document Analysis and Recognition, Curitiba, Brazil [BR], 2007","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W135592143","https://openalex.org/W1408813051","https://openalex.org/W1564409855","https://openalex.org/W1647671624","https://openalex.org/W2010595692","https://openalex.org/W2011656636","https://openalex.org/W2040062114","https://openalex.org/W2045566081","https://openalex.org/W2069189382","https://openalex.org/W2087382212","https://openalex.org/W2093476618","https://openalex.org/W2108985124","https://openalex.org/W2152335091","https://openalex.org/W2170727726","https://openalex.org/W4252090733","https://openalex.org/W6605604934","https://openalex.org/W6636915900"],"related_works":["https://openalex.org/W4306707571","https://openalex.org/W3163712264","https://openalex.org/W2389916653","https://openalex.org/W4391182771","https://openalex.org/W3179897446","https://openalex.org/W4309224528","https://openalex.org/W1562999394","https://openalex.org/W2970150031","https://openalex.org/W4362605793","https://openalex.org/W2980285880"],"abstract_inverted_index":{"With":[0],"the":[1,25,33,57],"increasing":[2],"market":[3],"of":[4,35,52,133],"cheap":[5],"cameras,":[6],"natural":[7,61,134],"scene":[8,62,135],"text":[9,22,36],"has":[10],"to":[11,47,60,93,122],"be":[12],"handled":[13],"in":[14,24,72],"an":[15,43],"efficient":[16],"way.":[17],"Some":[18],"works":[19],"deal":[20,94],"with":[21,95,143],"detection":[23],"image":[26],"while":[27],"more":[28],"recent":[29],"ones":[30,58],"point":[31],"out":[32],"challenge":[34],"extraction":[37],"and":[38,74,82,102,125],"recognition.":[39],"We":[40],"propose":[41],"here":[42],"OCR":[44,97,107],"correction":[45,126],"system":[46],"handle":[48],"tra-":[49],"ditional":[50],"issues":[51],"recognizer":[53],"errors":[54],"but":[55],"also":[56,140],"due":[59],"images,":[63],"i.e.":[64],"cut":[65],"characters,":[66],"artistic":[67],"display,":[68],"uncomplete":[69],"sentences":[70],"(present":[71],"advertisements)":[73],"out-":[75],"of-vocabulary":[76],"(OOV)":[77],"words":[78],"such":[79],"as":[80,106,112],"acronyms":[81],"so":[83],"on.":[84],"The":[85],"main":[86],"algorithm":[87],"bases":[88],"on":[89,129],"Finite-State":[90],"Machines":[91],"(FSMs)":[92],"learned":[96],"confusions,":[98],"capital/accented":[99],"let-":[100],"ters":[101],"lexicon":[103],"look-up.":[104],"Moreover,":[105],"is":[108],"not":[109],"consid-":[110],"ered":[111],"a":[113,130],"black":[114],"box,":[115],"several":[116],"outputs":[117],"are":[118,139],"taken":[119],"into":[120],"account":[121],"intermingle":[123],"recognition":[124],"steps.":[127],"Based":[128],"public":[131],"database":[132],"words,":[136],"detailed":[137],"results":[138],"presented":[141],"along":[142],"future":[144],"works.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}