{"id":"https://openalex.org/W2995333594","doi":"https://doi.org/10.1145/3368926.3369686","title":"OCR Error Correction for Unconstrained Vietnamese Handwritten Text","display_name":"OCR Error Correction for Unconstrained Vietnamese Handwritten Text","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2995333594","doi":"https://doi.org/10.1145/3368926.3369686","mag":"2995333594"},"language":"en","primary_location":{"id":"doi:10.1145/3368926.3369686","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","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/A5053018788","display_name":"Dung Nguyen","orcid":"https://orcid.org/0000-0003-1580-9032"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]},{"id":"https://openalex.org/I4210123993","display_name":"Van Lang University","ror":"https://ror.org/02ryrf141","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210123993"]}],"countries":["CZ","VN"],"is_corresponding":true,"raw_author_name":"Quoc-Dung Nguyen","raw_affiliation_strings":["Van Lang University, Ho Chi Minh, Vietnam, Technical University of Ostrava, Ostrava-Poruba, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Van Lang University, Ho Chi Minh, Vietnam, Technical University of Ostrava, Ostrava-Poruba, Czech Republic","institution_ids":["https://openalex.org/I142208455","https://openalex.org/I4210123993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058292518","display_name":"Anh Duc Le","orcid":"https://orcid.org/0000-0002-9359-9686"},"institutions":[{"id":"https://openalex.org/I203189479","display_name":"The Open University of Japan","ror":"https://ror.org/03jyr9x65","country_code":"JP","type":"education","lineage":["https://openalex.org/I203189479"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Duc-Anh Le","raw_affiliation_strings":["Center for Open Data in the Humanities, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Open Data in the Humanities, Tokyo, Japan","institution_ids":["https://openalex.org/I203189479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090445830","display_name":"Ivan Zelinka","orcid":"https://orcid.org/0000-0002-3858-7340"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ivan Zelinka","raw_affiliation_strings":["Technical University of Ostrava, Ostrava-Poruba, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Technical University of Ostrava, Ostrava-Poruba, Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053018788"],"corresponding_institution_ids":["https://openalex.org/I142208455","https://openalex.org/I4210123993"],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8485744,"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":"132","last_page":"138"},"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":0.9959999918937683,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9919000267982483,"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":0.8260218501091003},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7883267402648926},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7469594478607178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7089049816131592},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6672323942184448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.586592435836792},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.571450412273407},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5510278344154358},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.49810123443603516},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.49700573086738586},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48010969161987305},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4691646993160248},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4233614206314087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4008592963218689},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17359936237335205},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15136873722076416},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.14858832955360413},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07126873731613159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260218501091003},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7883267402648926},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7469594478607178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7089049816131592},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6672323942184448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586592435836792},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.571450412273407},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5510278344154358},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.49810123443603516},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.49700573086738586},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48010969161987305},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4691646993160248},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4233614206314087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4008592963218689},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17359936237335205},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15136873722076416},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.14858832955360413},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07126873731613159},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368926.3369686","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology  - SoICT 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W415355213","https://openalex.org/W1626689694","https://openalex.org/W1977877104","https://openalex.org/W1978469901","https://openalex.org/W1993301141","https://openalex.org/W2000020734","https://openalex.org/W2045929671","https://openalex.org/W2049516752","https://openalex.org/W2100120110","https://openalex.org/W2117877951","https://openalex.org/W2120788366","https://openalex.org/W2122585011","https://openalex.org/W2134253153","https://openalex.org/W2167898728","https://openalex.org/W2462421214","https://openalex.org/W2578485521","https://openalex.org/W2791089502","https://openalex.org/W2809468489","https://openalex.org/W2901878905","https://openalex.org/W2906436882","https://openalex.org/W2906810737","https://openalex.org/W2955124706","https://openalex.org/W2964322605"],"related_works":["https://openalex.org/W2108932455","https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W2013767392","https://openalex.org/W3190162935","https://openalex.org/W2390197506","https://openalex.org/W2892857623","https://openalex.org/W2595338207","https://openalex.org/W1973075426","https://openalex.org/W2135329887"],"abstract_inverted_index":{"Post-processing":[0],"is":[1],"an":[2,18,114],"essential":[3],"step":[4],"in":[5,10,145],"detecting":[6],"and":[7,28,47,54,99,111,120],"correcting":[8],"errors":[9,56],"OCR-generated":[11],"texts.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16],"present":[17],"automatic":[19],"OCR":[20,33,69],"post-processing":[21],"model":[22,75,91],"which":[23,106],"comprises":[24],"both":[25,52,109],"error":[26,29,66,96,103],"detection":[27],"correction":[30,49],"phases":[31],"for":[32,51],"output":[34],"texts":[35],"of":[36,45,68,94,101,113,127],"unconstrained":[37],"Vietnamese":[38,78,129],"handwriting.":[39],"We":[40,71],"propose":[41],"a":[42,77],"hybrid":[43],"approach":[44,117],"generating":[46],"scoring":[48],"candidates":[50],"non-syllable":[53],"real-syllable":[55],"based":[57],"on":[58,76,123],"the":[59,65,82,124,128,146],"linguistic":[60],"features":[61],"as":[62,64],"well":[63],"characteristics":[67],"outputs.":[70],"evaluate":[72],"our":[73,90],"proposed":[74],"benchmark":[79],"database":[80],"at":[81],"line":[83],"level.":[84],"The":[85],"experimental":[86],"results":[87,137],"show":[88],"that":[89],"achieves":[92],"4.17%":[93],"character":[95],"rate":[97,104],"(CER)":[98],"9.82%":[100],"word":[102],"(WER),":[105],"helps":[107],"improve":[108],"CER":[110],"WER":[112],"attention-based":[115],"encoder-decoder":[116],"by":[118,141],"0.5%":[119],"3.5%":[121],"respectively":[122],"VNOnDB-Line":[125],"dataset":[126],"online":[130],"handwritten":[131],"text":[132],"recognition":[133,143],"competition":[134],"(VOHTR2018).":[135],"These":[136],"outperform":[138],"those":[139],"obtained":[140],"various":[142],"systems":[144],"VOHTR2018":[147],"competition.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}