{"id":"https://openalex.org/W4296211656","doi":"https://doi.org/10.1109/access.2022.3207469","title":"A Transformer-Based Framework for Scene Text Recognition","display_name":"A Transformer-Based Framework for Scene Text Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4296211656","doi":"https://doi.org/10.1109/access.2022.3207469"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3207469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3207469","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09894408.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09894408.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101841386","display_name":"Prabu Selvam","orcid":"https://orcid.org/0000-0003-1804-1401"},"institutions":[{"id":"https://openalex.org/I932239252","display_name":"SASTRA University","ror":"https://ror.org/032jk8892","country_code":"IN","type":"education","lineage":["https://openalex.org/I932239252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prabu Selvam","raw_affiliation_strings":["School of Computing, SASTRA Deemed University, Thanjavur, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, SASTRA Deemed University, Thanjavur, Tamil Nadu, India","institution_ids":["https://openalex.org/I932239252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joseph Abraham Sundar Koilraj","orcid":null},"institutions":[{"id":"https://openalex.org/I932239252","display_name":"SASTRA University","ror":"https://ror.org/032jk8892","country_code":"IN","type":"education","lineage":["https://openalex.org/I932239252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Joseph Abraham Sundar Koilraj","raw_affiliation_strings":["School of Computing, SASTRA Deemed University, Thanjavur, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, SASTRA Deemed University, Thanjavur, Tamil Nadu, India","institution_ids":["https://openalex.org/I932239252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009125561","display_name":"Carlos Andr\u00e9s Tavera Romero","orcid":"https://orcid.org/0000-0002-4606-7222"},"institutions":[{"id":"https://openalex.org/I4210091828","display_name":"Universidad Santiago de Cali","ror":"https://ror.org/00dxj9a45","country_code":"CO","type":"education","lineage":["https://openalex.org/I4210091828"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Carlos Andres Tavera Romero","raw_affiliation_strings":["COMBA R&D Laboratory, Faculty of Engineering, Universidad Santiago de Cali, Cali, Colombia"],"raw_orcid":"https://orcid.org/0000-0002-4606-7222","affiliations":[{"raw_affiliation_string":"COMBA R&D Laboratory, Faculty of Engineering, Universidad Santiago de Cali, Cali, Colombia","institution_ids":["https://openalex.org/I4210091828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030500450","display_name":"Meshal Alharbi","orcid":"https://orcid.org/0000-0002-6025-7858"},"institutions":[{"id":"https://openalex.org/I142608572","display_name":"Prince Sattam Bin Abdulaziz University","ror":"https://ror.org/04jt46d36","country_code":"SA","type":"education","lineage":["https://openalex.org/I142608572"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Meshal Alharbi","raw_affiliation_strings":["Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6025-7858","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia","institution_ids":["https://openalex.org/I142608572"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013760675","display_name":"Abolfazl Mehbodniya","orcid":"https://orcid.org/0000-0002-0945-512X"},"institutions":[{"id":"https://openalex.org/I4210111408","display_name":"Kuwait College of Science and Technology","ror":"https://ror.org/01vjvsj67","country_code":"KW","type":"education","lineage":["https://openalex.org/I4210111408"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Abolfazl Mehbodniya","raw_affiliation_strings":["Department of Electronics and Communications Engineering, Kuwait College of Science and Technology, Safat, Kuwait"],"raw_orcid":"https://orcid.org/0000-0002-0945-512X","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communications Engineering, Kuwait College of Science and Technology, Safat, Kuwait","institution_ids":["https://openalex.org/I4210111408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088969893","display_name":"Julian Webber","orcid":"https://orcid.org/0000-0001-7796-2898"},"institutions":[{"id":"https://openalex.org/I4210111408","display_name":"Kuwait College of Science and Technology","ror":"https://ror.org/01vjvsj67","country_code":"KW","type":"education","lineage":["https://openalex.org/I4210111408"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Julian L. Webber","raw_affiliation_strings":["Department of Electronics and Communications Engineering, Kuwait College of Science and Technology, Safat, Kuwait"],"raw_orcid":"https://orcid.org/0000-0001-7796-2898","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communications Engineering, Kuwait College of Science and Technology, Safat, Kuwait","institution_ids":["https://openalex.org/I4210111408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082920406","display_name":"Sudhakar Sengan","orcid":"https://orcid.org/0000-0003-4901-1432"},"institutions":[{"id":"https://openalex.org/I118826373","display_name":"Tirunelveli Medical College","ror":"https://ror.org/01c4srk95","country_code":"IN","type":"education","lineage":["https://openalex.org/I118826373"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudhakar Sengan","raw_affiliation_strings":["Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0003-4901-1432","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, Tamil Nadu, India","institution_ids":["https://openalex.org/I118826373"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.7541,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92099048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"100895","last_page":"100910"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.995199978351593,"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":0.9937999844551086,"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":0.8300390243530273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6690734624862671},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6507644653320312},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5709016919136047},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.521202027797699},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5207890868186951},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4943974018096924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4866657853126526},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4561518728733063},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43322494626045227},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4173774719238281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08993560075759888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300390243530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6690734624862671},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6507644653320312},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5709016919136047},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.521202027797699},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5207890868186951},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4943974018096924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4866657853126526},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4561518728733063},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43322494626045227},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4173774719238281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08993560075759888},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":2,"locations":[{"id":"doi:10.1109/access.2022.3207469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3207469","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09894408.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9b894ef84bb94ebaa1565d17a2c2421f","is_oa":true,"landing_page_url":"https://doaj.org/article/9b894ef84bb94ebaa1565d17a2c2421f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 100895-100910 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3207469","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3207469","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09894408.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4000000059604645,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6491834631","display_name":null,"funder_award_id":"01-2022","funder_id":"https://openalex.org/F4320319861","funder_display_name":"Universidad Santiago de Cali"}],"funders":[{"id":"https://openalex.org/F4320319861","display_name":"Universidad Santiago de Cali","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296211656.pdf","grobid_xml":"https://content.openalex.org/works/W4296211656.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W367930861","https://openalex.org/W654550266","https://openalex.org/W1971822075","https://openalex.org/W1978729128","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2135231474","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2750938222","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2892009249","https://openalex.org/W2911295582","https://openalex.org/W2963233387","https://openalex.org/W2963327605","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2970910956","https://openalex.org/W2978036638","https://openalex.org/W2980487166","https://openalex.org/W3013224334","https://openalex.org/W3025830232","https://openalex.org/W3035449864","https://openalex.org/W3043311956","https://openalex.org/W3082397598","https://openalex.org/W3092309237","https://openalex.org/W3097932944","https://openalex.org/W3106271744","https://openalex.org/W3159954715","https://openalex.org/W3188982915","https://openalex.org/W3196665767","https://openalex.org/W4229440871","https://openalex.org/W4285791503","https://openalex.org/W4291734217","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6629590909","https://openalex.org/W6636382570","https://openalex.org/W6739901393","https://openalex.org/W6751097180","https://openalex.org/W6753640285"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W4220731478","https://openalex.org/W2095030957","https://openalex.org/W2066827917"],"abstract_inverted_index":{"Scene":[0],"Text":[1],"Recognition":[2],"(STR)":[3],"has":[4],"become":[5],"a":[6,46,88,153,224,237,294],"popular":[7],"and":[8,54,83,175,213,247,256,277],"long-standing":[9],"research":[10,42],"problem":[11],"in":[12,94,114,182,195,231,253],"computer":[13],"vision":[14],"communities.":[15],"Almost":[16],"all":[17],"the":[18,23,64,95,101,107,115,122,135,140,168,172,183,188,196,216,232,245,250,290],"existing":[19,31,291],"approaches":[20,32,292],"mainly":[21],"adopt":[22],"connectionist":[24],"temporal":[25],"classification":[26],"(CTC)":[27],"technique.":[28],"However,":[29,139],"these":[30],"are":[33,148,178],"not":[34,149],"much":[35],"effective":[36],"for":[37,151],"irregular":[38,55],"STR.":[39],"In":[40],"this":[41],"article,":[43],"we":[44,86,118,222],"introduced":[45],"new":[47,225],"encoder-decoder":[48],"framework":[49,69,199,252,286],"to":[50,99,105,128,166,208,235],"identify":[51],"both":[52,254],"regular":[53],"natural":[56],"scene":[57],"text,":[58],"which":[59],"is":[60,70],"developed":[61],"based":[62],"on":[63,156,215,263],"transformer":[65,198],"framework.":[66],"The":[67],"proposed":[68,161,251,285],"divided":[71],"into":[72],"four":[73],"main":[74],"modules:":[75],"Image":[76],"Transformation,":[77],"Visual":[78],"Feature":[79],"Extraction":[80],"(VFE),":[81],"Encoder":[82],"Decoder.":[84],"Firstly,":[85],"employ":[87],"Thin":[89],"Plate":[90],"Spline":[91],"(TPS)":[92],"transformation":[93,97,177],"image":[96,104,131],"module":[98,142,234],"normalize":[100],"original":[102,189],"input":[103],"reduce":[106],"burden":[108],"of":[109,249,289],"subsequent":[110],"feature":[111,145,173,176],"extraction.":[112],"Secondly,":[113],"VFE":[116,141],"module,":[117],"use":[119],"ResNet":[120],"as":[121,194],"Convolutional":[123],"Neural":[124],"Network":[125],"(CNN)":[126],"backbone":[127],"retrieve":[129],"text":[130,155,219,258],"features":[132],"maps":[133,146],"from":[134],"rectified":[136],"word":[137,158],"image.":[138],"generates":[143],"one-dimensional":[144],"that":[147,283],"suitable":[150],"locating":[152],"multi-oriented":[154],"two-dimensional":[157],"images.":[159],"We":[160,186,243,280],"2D":[162],"Positional":[163],"Encoding":[164],"(2DPE)":[165],"preserve":[167],"sequential":[169],"information.":[170],"Thirdly,":[171],"aggregation":[174],"carried":[179],"out":[180],"simultaneously":[181],"encoder":[184],"module.":[185],"replace":[187],"scaled":[190],"dot-product":[191],"attention":[192],"model":[193,207],"standard":[197],"with":[200],"an":[201],"Optimal":[202],"Adaptive":[203],"Threshold-based":[204],"Self-Attention":[205],"(OATSA)":[206],"filter":[209],"noisy":[210],"information":[211],"effectively":[212],"focus":[214],"most":[217,288],"contributive":[218],"regions.":[220],"Finally,":[221],"introduce":[223],"architectural":[226],"level":[227],"bi-directional":[228],"decoding":[229],"approach":[230],"decoder":[233],"generate":[236],"more":[238],"accurate":[239],"character":[240],"sequence.":[241],"Eventually,":[242],"evaluate":[244],"effectiveness":[246],"robustness":[248],"horizontal":[255],"arbitrary":[257],"recognition":[259],"through":[260],"extensive":[261],"experiments":[262],"seven":[264],"public":[265],"benchmarks":[266],"including":[267],"IIIT5K-Words,":[268],"SVT,":[269],"ICDAR":[270,272,274],"2003,":[271],"2013,":[273],"2015,":[275],"SVT-P":[276],"CUTE80":[278],"datasets.":[279],"also":[281],"demonstrate":[282],"our":[284],"outperforms":[287],"by":[293],"substantial":[295],"margin.":[296]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}