{"id":"https://openalex.org/W1996960689","doi":"https://doi.org/10.1145/2505377.2505382","title":"HMM-based script identification for OCR","display_name":"HMM-based script identification for OCR","publication_year":2013,"publication_date":"2013-08-24","ids":{"openalex":"https://openalex.org/W1996960689","doi":"https://doi.org/10.1145/2505377.2505382","mag":"1996960689"},"language":"en","primary_location":{"id":"doi:10.1145/2505377.2505382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505377.2505382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multilingual OCR","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/A5048470138","display_name":"Dmitriy Genzel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitriy Genzel","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078560039","display_name":"Ashok C. Popat","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok C. Popat","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021837944","display_name":"Remco Teunen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Remco Teunen","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102171465","display_name":"Yasuhisa Fujii","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasuhisa Fujii","raw_affiliation_strings":["Google, Inc., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9905999898910522,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9876999855041504,"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/scripting-language","display_name":"Scripting language","score":0.8610737323760986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8389487266540527},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.825702428817749},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6498360633850098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6290469765663147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5928804874420166},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5562762022018433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5312041640281677},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5299212336540222},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5226882696151733},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4794993996620178},{"id":"https://openalex.org/keywords/typeface","display_name":"Typeface","score":0.4744240641593933},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11875796318054199},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07106804847717285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06231117248535156}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8610737323760986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389487266540527},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.825702428817749},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6498360633850098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290469765663147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5928804874420166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5562762022018433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5312041640281677},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5299212336540222},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5226882696151733},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4794993996620178},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.4744240641593933},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11875796318054199},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07106804847717285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06231117248535156},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":1,"locations":[{"id":"doi:10.1145/2505377.2505382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505377.2505382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multilingual OCR","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1980382462","https://openalex.org/W2003334993","https://openalex.org/W2059523408","https://openalex.org/W2075546307","https://openalex.org/W2119123874","https://openalex.org/W2153349796","https://openalex.org/W2168231600","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W2164215946","https://openalex.org/W2120407907","https://openalex.org/W2016860631","https://openalex.org/W2895456681","https://openalex.org/W4289422041","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"While":[0],"current":[1],"OCR":[2,44,66,71,100,131,155],"systems":[3],"are":[4,110,179],"able":[5],"to":[6,21,45,104],"recognize":[7,105],"text":[8],"in":[9,24,62,76,86],"an":[10,34,169],"increasing":[11],"number":[12],"of":[13,48,84,147,167,171],"scripts":[14,28],"and":[15,29,115,128],"languages,":[16],"typically":[17],"they":[18],"still":[19],"need":[20],"be":[22],"told":[23],"advance":[25],"what":[26],"those":[27],"languages":[30,75,178],"are.":[31],"We":[32,59],"propose":[33],"approach":[35],"that":[36],"repurposes":[37],"the":[38,46,137,158,174,177],"same":[39],"HMM-based":[40,99],"system":[41,101,140,156,161],"used":[42],"for":[43,124,129,149],"task":[47],"script/language":[49],"ID,":[50],"by":[51],"replacing":[52],"character":[53,164],"labels":[54],"with":[55,157],"script":[56,125,138,143,159],"class":[57],"labels.":[58],"apply":[60],"it":[61],"a":[63,81,93,97,113,142,163,181],"multi-pass":[64],"overall":[65,130],"process":[67],"which":[68],"achieves":[69],"\"universal\"":[70],"over":[72,80,173],"54":[73],"tested":[74],"18":[77,150],"distinct":[78,151],"scripts,":[79],"wide":[82],"variety":[83],"typefaces":[85],"each.":[87],"For":[88],"comparison":[89],"we":[90],"also":[91],"consider":[92],"brute-force":[94],"approach,":[95],"wherein":[96],"singe":[98],"is":[102],"trained":[103],"all":[106],"considered":[107],"scripts.":[108,152],"Results":[109],"presented":[111],"on":[112],"large":[114],"diverse":[116],"evaluation":[117,135],"set":[118],"extracted":[119],"from":[120],"book":[121],"images,":[122],"both":[123],"identification":[126],"accuracy":[127],"accuracy.":[132],"On":[133],"this":[134],"data,":[136],"ID":[139,144,160],"provided":[141],"error":[145,165],"rate":[146,166],"1.73%":[148],"The":[153],"end-to-end":[154],"achieved":[162],"4.05%,":[168],"increase":[170],"0.77%":[172],"case":[175],"where":[176],"known":[180],"priori.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}