{"id":"https://openalex.org/W4309675586","doi":"https://doi.org/10.1109/kse56063.2022.9953789","title":"Vietnamese Text Detection, Recognition and Classification in Images","display_name":"Vietnamese Text Detection, Recognition and Classification in Images","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4309675586","doi":"https://doi.org/10.1109/kse56063.2022.9953789"},"language":"en","primary_location":{"id":"doi:10.1109/kse56063.2022.9953789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse56063.2022.9953789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","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/A5022075063","display_name":"Tuan Le Xuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuan Le Xuan","raw_affiliation_strings":["People&#x2019;s Security Academy,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"People&#x2019;s Security Academy,Hanoi,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083433168","display_name":"Hang Pham Thi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Pham Thi","raw_affiliation_strings":["People&#x2019;s Security Academy,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"People&#x2019;s Security Academy,Hanoi,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088039595","display_name":"Hai V. Nguyen","orcid":"https://orcid.org/0000-0002-2578-170X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hai Nguyen Do","raw_affiliation_strings":["People&#x2019;s Security Academy,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"People&#x2019;s Security Academy,Hanoi,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022075063"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1008,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3947594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.992900013923645,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9905999898910522,"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":0.8010057806968689},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.6777785420417786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6694869995117188},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5231284499168396},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5181652307510376},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.49735596776008606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47088178992271423},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.46339207887649536},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4536735713481903},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4448191225528717},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4224601984024048},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4128193259239197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39767661690711975},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3852219581604004},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2341688573360443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010057806968689},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.6777785420417786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6694869995117188},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5231284499168396},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5181652307510376},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.49735596776008606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47088178992271423},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.46339207887649536},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4536735713481903},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4448191225528717},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4224601984024048},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4128193259239197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39767661690711975},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3852219581604004},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2341688573360443},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse56063.2022.9953789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse56063.2022.9953789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1565201084","https://openalex.org/W1686810756","https://openalex.org/W2279655419","https://openalex.org/W2888746867","https://openalex.org/W2896457183","https://openalex.org/W2904147048","https://openalex.org/W2967615747","https://openalex.org/W2982243523","https://openalex.org/W2990217975","https://openalex.org/W2998404685","https://openalex.org/W3003711889","https://openalex.org/W3007671050","https://openalex.org/W3130456057","https://openalex.org/W4206740823","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6695114890","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6771836014"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W4221004363","https://openalex.org/W2963299604","https://openalex.org/W3163712264","https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W4387168087","https://openalex.org/W3107028621","https://openalex.org/W1606434116","https://openalex.org/W2116355940"],"abstract_inverted_index":{"Detecting":[0],"and":[1,36,42,55,58,75,137,195,198],"recognizing":[2,196],"text":[3,44,78,117,122,139,151,161,164,197,202],"in":[4,22,79,88,118,128,133,140,193,200],"images":[5,46,80,96,162],"is":[6],"a":[7,12,69],"task":[8],"that":[9,182],"has":[10,186],"received":[11],"lot":[13],"of":[14,60,175,189],"attention":[15,52],"recently":[16],"due":[17],"to":[18,53,72,85,109,113,149,158,191],"its":[19],"high":[20],"applicability":[21],"many":[23],"fields":[24],"such":[25],"as":[26,94,132],"digitization,":[27],"storage,":[28],"lookup,":[29],"authentication":[30],"However,":[31],"most":[32],"current":[33],"research":[34],"works":[35],"products":[37],"are":[38],"focusing":[39],"on":[40,204],"detecting":[41,194],"extracting":[43],"from":[45,82],"but":[47],"not":[48],"paying":[49],"very":[50],"much":[51],"analyzing":[54],"exploiting":[56],"semantics":[57],"nuances":[59,203],"those":[61],"extracted":[62,146],"texts.":[63],"In":[64],"this":[65],"study,":[66],"we":[67,154],"propose":[68],"three-in-one":[70],"system":[71,92],"detect,":[73],"recognize":[74],"classify":[76],"Vietnamese":[77,98],"collected":[81,206],"social":[83],"media":[84],"help":[86],"authorities":[87],"monitoring":[89],"tasks.":[90],"The":[91],"receives":[93],"input":[95],"containing":[97,116],"text,":[99],"uses":[100],"the":[101,119,129,134,138,141,150,183,205],"Character-Region":[102],"Awareness":[103],"For":[104],"Text":[105],"detection":[106],"(CRAFT)":[107],"model":[108,157,185],"perform":[110],"background":[111],"processing":[112],"produce":[114],"areas":[115],"image;":[120],"these":[121,160,167],"containers":[123],"will":[124,143,169],"then":[125],"be":[126,145,170],"rearranged":[127],"same":[130],"order":[131],"original":[135],"image,":[136],"image":[142],"also":[144],"out":[147],"according":[148],"container.":[152],"Next,":[153],"use":[155],"VietOCR":[156],"convert":[159],"into":[163],"fragments.":[165],"Finally,":[166],"texts":[168],"classified":[171],"using":[172],"an":[173,187],"ensemble":[174],"machine":[176],"learning":[177],"models.":[178],"Preliminary":[179],"results":[180],"show":[181],"proposed":[184],"accuracy":[188],"up":[190],"88.0%":[192],"94%":[199],"classifying":[201],"data":[207],"set.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
