{"id":"https://openalex.org/W4312419898","doi":"https://doi.org/10.1145/3558100.3563845","title":"Optical character recognition with transformers and CTC","display_name":"Optical character recognition with transformers and CTC","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4312419898","doi":"https://doi.org/10.1145/3558100.3563845"},"language":"en","primary_location":{"id":"doi:10.1145/3558100.3563845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558100.3563845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Symposium on Document Engineering","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/A5039444907","display_name":"Israel Campiotti","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Israel Campiotti","raw_affiliation_strings":["University of Campinas"],"affiliations":[{"raw_affiliation_string":"University of Campinas","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087970571","display_name":"Roberto Lotufo","orcid":"https://orcid.org/0000-0002-5652-0852"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Roberto Lotufo","raw_affiliation_strings":["University of Campinas"],"affiliations":[{"raw_affiliation_string":"University of Campinas","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039444907"],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.4025,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60439806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9961000084877014,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9947999715805054,"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":0.7633557319641113},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6809842586517334},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6050622463226318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011040806770325},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4989738464355469},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4919387996196747},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48939433693885803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4837227165699005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32058197259902954},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08833768963813782},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06337451934814453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633557319641113},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6809842586517334},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6050622463226318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011040806770325},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4989738464355469},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4919387996196747},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48939433693885803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4837227165699005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32058197259902954},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08833768963813782},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06337451934814453},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3558100.3563845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558100.3563845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2133564696","https://openalex.org/W2194187530","https://openalex.org/W2741147179","https://openalex.org/W2893345206","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2995752927","https://openalex.org/W3087858202","https://openalex.org/W3170863103","https://openalex.org/W3199928321","https://openalex.org/W3207037366","https://openalex.org/W3217248625","https://openalex.org/W4212804231","https://openalex.org/W4285213101","https://openalex.org/W4294629828","https://openalex.org/W6783441721","https://openalex.org/W6796761347","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4375867731","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Text":[0],"recognition":[1],"tasks":[2],"are":[3],"commonly":[4],"solved":[5],"by":[6,25,98,201],"using":[7,140,204],"a":[8,18,21,26,30,45,63,91,94,99,134],"deep":[9],"learning":[10],"pipeline":[11,55],"called":[12],"CRNN.":[13],"The":[14,84,102],"classical":[15],"CRNN":[16,46],"is":[17,50,90,129,194],"sequence":[19],"of":[20,41,44,70,81,93,125,148,171,187,197],"convolutional":[22,95,116],"network,":[23],"followed":[24,97],"bidirectional":[27],"LSTM":[28],"and":[29,56,118,154,208],"CTC":[31,100,120,142,166,182],"layer.":[32,101,121],"In":[33],"this":[34,128],"paper,":[35],"we":[36,73,152],"perform":[37],"an":[38,111,168,184],"extensive":[39],"analysis":[40],"the":[42,53,68,79,115,119,123,130,146,158,198,202],"components":[43],"to":[47,52],"find":[48],"what":[49,57],"crucial":[51],"entire":[54],"characteristics":[58],"can":[59],"be":[60],"exchanged":[61],"for":[62,78,215],"more":[64,209],"effective":[65],"choice.":[66],"Given":[67],"results":[69],"our":[71,126,149],"experiments,":[72],"propose":[74],"two":[75],"different":[76],"architectures":[77],"task":[80],"text":[82],"recognition.":[83],"first":[85,131],"model,":[86,104],"CNN":[87,105,164,178],"+":[88,106,108,165,179,181],"CTC,":[89,109],"combination":[92],"model":[96],"second":[103],"Tr":[107,180],"adds":[110],"encoder-only":[112],"Transformers":[113,135],"between":[114],"network":[117],"To":[122,144],"best":[124],"knowledge,":[127],"time":[132],"that":[133],"have":[136],"been":[137],"successfully":[138],"trained":[139],"just":[141],"loss.":[143],"assess":[145],"capabilities":[147],"proposed":[150],"architectures,":[151],"train":[153],"evaluate":[155],"them":[156],"on":[157],"SROIE":[159],"2019":[160],"data":[161],"set.":[162],"Our":[163],"achieves":[167],"F1":[169,185],"score":[170,186],"89.66%":[172],"possessing":[173],"only":[174],"4.7":[175],"million":[176,191,206,212],"parameters.":[177],"attained":[183],"93.76%":[188],"with":[189],"11":[190],"parameters,":[192],"which":[193],"almost":[195],"97%":[196],"performance":[199],"achieved":[200],"TrOCR":[203],"334":[205],"parameters":[207],"than":[210],"600":[211],"synthetic":[213],"images":[214],"pretraining.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}