{"id":"https://openalex.org/W3048948626","doi":"https://doi.org/10.1142/s0219691320500526","title":"Improvement of the end-to-end scene text recognition method for \u201ctext-to-speech\u201d conversion","display_name":"Improvement of the end-to-end scene text recognition method for \u201ctext-to-speech\u201d conversion","publication_year":2020,"publication_date":"2020-08-12","ids":{"openalex":"https://openalex.org/W3048948626","doi":"https://doi.org/10.1142/s0219691320500526","mag":"3048948626"},"language":"en","primary_location":{"id":"doi:10.1142/s0219691320500526","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691320500526","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","raw_type":"journal-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/A5017599793","display_name":"Fazliddin Makhmudov","orcid":null},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Fazliddin Makhmudov","raw_affiliation_strings":["Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea"],"affiliations":[{"raw_affiliation_string":"Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea","institution_ids":["https://openalex.org/I12832649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054140053","display_name":"Mukhriddin Mukhiddinov","orcid":"https://orcid.org/0000-0002-1424-0799"},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Mukhriddin Mukhiddinov","raw_affiliation_strings":["Department of Hardware and Software of Control Systems in Telecommunications, Tashkent University of Information Technologies, named after Muhammad al-Khwarizmi, Tashkent, 100200, Uzbekistan"],"affiliations":[{"raw_affiliation_string":"Department of Hardware and Software of Control Systems in Telecommunications, Tashkent University of Information Technologies, named after Muhammad al-Khwarizmi, Tashkent, 100200, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036343089","display_name":"Akmalbek Abdusalomov","orcid":"https://orcid.org/0000-0001-5923-8695"},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Akmalbek Abdusalomov","raw_affiliation_strings":["Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea"],"affiliations":[{"raw_affiliation_string":"Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea","institution_ids":["https://openalex.org/I12832649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034565243","display_name":"Kuldoshbay Avazov","orcid":null},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kuldoshbay Avazov","raw_affiliation_strings":["Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea"],"affiliations":[{"raw_affiliation_string":"Department of IT Convergence Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea","institution_ids":["https://openalex.org/I12832649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040206956","display_name":"Utkir Khamdamov","orcid":"https://orcid.org/0000-0001-7038-9793"},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Utkir Khamdamov","raw_affiliation_strings":["Department of Hardware and Software of Control Systems in Telecommunications, Tashkent University of Information Technologies, named after Muhammad al-Khwarizmi, Tashkent, 100200, Uzbekistan"],"affiliations":[{"raw_affiliation_string":"Department of Hardware and Software of Control Systems in Telecommunications, Tashkent University of Information Technologies, named after Muhammad al-Khwarizmi, Tashkent, 100200, Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023896107","display_name":"Young Im Cho","orcid":"https://orcid.org/0000-0003-0184-7599"},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Im Cho","raw_affiliation_strings":["Department of Computer Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, 461-701, Korea","institution_ids":["https://openalex.org/I12832649"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017599793"],"corresponding_institution_ids":["https://openalex.org/I12832649"],"apc_list":null,"apc_paid":null,"fwci":2.0517,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.8912079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"18","issue":"06","first_page":"2050052","last_page":"2050052"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8502162098884583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7499303221702576},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6195695400238037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5326036810874939},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5270127058029175},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5230506658554077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46518129110336304},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46260082721710205},{"id":"https://openalex.org/keywords/uzbek","display_name":"Uzbek","score":0.4581204652786255},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44732049107551575},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.44249698519706726},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.41881367564201355},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2968921363353729},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08983129262924194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502162098884583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7499303221702576},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6195695400238037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5326036810874939},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5270127058029175},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5230506658554077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46518129110336304},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46260082721710205},{"id":"https://openalex.org/C2778718127","wikidata":"https://www.wikidata.org/wiki/Q9264","display_name":"Uzbek","level":2,"score":0.4581204652786255},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44732049107551575},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.44249698519706726},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.41881367564201355},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2968921363353729},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08983129262924194},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219691320500526","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691320500526","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1972065312","https://openalex.org/W2001642682","https://openalex.org/W2102003408","https://openalex.org/W2119162941","https://openalex.org/W2131163834","https://openalex.org/W2133059825","https://openalex.org/W2134973740","https://openalex.org/W2136730584","https://openalex.org/W2194187530","https://openalex.org/W2217433794","https://openalex.org/W2294797155","https://openalex.org/W2586807479","https://openalex.org/W2605076167","https://openalex.org/W2746334984","https://openalex.org/W2750938222","https://openalex.org/W2798450692","https://openalex.org/W2810983211","https://openalex.org/W2891656133","https://openalex.org/W2912697496","https://openalex.org/W2923054028","https://openalex.org/W2952365771","https://openalex.org/W2952439627","https://openalex.org/W2952555815","https://openalex.org/W3009202695","https://openalex.org/W3024062944","https://openalex.org/W4247658683","https://openalex.org/W6601250092"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W4221004363","https://openalex.org/W2963299604","https://openalex.org/W3211262047","https://openalex.org/W950386562","https://openalex.org/W2363517123","https://openalex.org/W3012395971","https://openalex.org/W2894624991","https://openalex.org/W2949229884","https://openalex.org/W2777652944"],"abstract_inverted_index":{"Methods":[0],"for":[1,47,154],"text":[2,43,67,72,92,115,149],"detection":[3,44,68],"and":[4,20,41,45,60,103,136,139,147],"recognition":[5,46,93],"in":[6,17,51,73,76,144],"images":[7,54,78,153],"of":[8],"natural":[9,52,151],"scenes":[10],"have":[11,21],"become":[12],"an":[13,142],"active":[14],"research":[15],"topic":[16],"computer":[18],"vision":[19],"obtained":[22],"encouraging":[23],"achievements":[24],"over":[25],"several":[26],"benchmarks.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"introduce":[32],"a":[33,56,80,107],"robust":[34],"yet":[35],"simple":[36],"pipeline":[37],"that":[38],"produces":[39],"accurate":[40],"fast":[42],"the":[48,61,66,91,96,101,113,120,131,156],"Uzbek":[49,97,121],"language":[50,122],"scene":[53,152],"using":[55,106,119],"fully":[57,82],"convolutional":[58,83],"network":[59],"Tesseract":[62,109],"OCR":[63,110],"engine.":[64,111],"First,":[65],"step":[69,94],"quickly":[70],"predicts":[71],"random":[74],"orientations":[75],"full-color":[77],"with":[79],"single":[81],"neural":[84],"network,":[85],"discarding":[86],"redundant":[87],"intermediate":[88],"stages.":[89],"Then,":[90],"recognizes":[95],"language,":[98],"including":[99],"both":[100],"Latin":[102],"Cyrillic":[104],"alphabets,":[105],"trained":[108],"Finally,":[112],"recognized":[114],"can":[116],"be":[117],"pronounced":[118],"text-to-speech":[123],"synthesizer.":[124],"The":[125],"proposed":[126],"method":[127],"was":[128],"tested":[129],"on":[130],"ICDAR":[132,134],"2013,":[133],"2015":[135],"MSRA-TD500":[137],"datasets,":[138],"it":[140],"showed":[141],"advantage":[143],"efficiently":[145],"detecting":[146],"recognizing":[148],"from":[150],"assisting":[155],"visually":[157],"impaired.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
