{"id":"https://openalex.org/W7165541828","doi":"https://doi.org/10.1109/access.2026.3705442","title":"Beyond Simple Character Recognition: A Comparative Study of Vision-Language Models and Dedicated OCR Systems in Edge Cases","display_name":"Beyond Simple Character Recognition: A Comparative Study of Vision-Language Models and Dedicated OCR Systems in Edge Cases","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165541828","doi":"https://doi.org/10.1109/access.2026.3705442"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3705442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3705442","pdf_url":null,"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://doi.org/10.1109/access.2026.3705442","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041027404","display_name":"Junsu Kim","orcid":"https://orcid.org/0000-0001-9583-7978"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juran Kim","raw_affiliation_strings":["Google Infra Team, Sortech, Busan, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-0865-1162","affiliations":[{"raw_affiliation_string":"Google Infra Team, Sortech, Busan, Republic of Korea","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139124982","display_name":"Chang Yong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang-Young Lee","raw_affiliation_strings":["Google AI Team, Sortech, Busan, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI Team, Sortech, Busan, Republic of Korea","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029245991","display_name":"Chang Yup Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147997","display_name":"Busan TechnoPark","ror":"https://ror.org/05mw5z210","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210147997"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang-Yup Han","raw_affiliation_strings":["CEO, Sortech, Busan, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEO, Sortech, Busan, Republic of Korea","institution_ids":["https://openalex.org/I4210147997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016249429","display_name":"Nam\u2010Hyun Yoo","orcid":"https://orcid.org/0000-0003-2161-9251"},"institutions":[{"id":"https://openalex.org/I71007489","display_name":"Kyungnam University","ror":"https://ror.org/037pkxm09","country_code":"KR","type":"education","lineage":["https://openalex.org/I71007489"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam-Hyun Yoo","raw_affiliation_strings":["Department of Computer Engineering, Kyungnam University, Changwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2161-9251","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kyungnam University, Changwon, Republic of Korea","institution_ids":["https://openalex.org/I71007489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114860745","display_name":"Jinhong Yang","orcid":"https://orcid.org/0000-0002-7756-0263"},"institutions":[{"id":"https://openalex.org/I104338594","display_name":"Inje University","ror":"https://ror.org/04xqwq985","country_code":"KR","type":"education","lineage":["https://openalex.org/I104338594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhong Yang","raw_affiliation_strings":["Department of Medical Information Technology, Inje University, Gimhae, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7756-0263","affiliations":[{"raw_affiliation_string":"Department of Medical Information Technology, Inje University, Gimhae, Republic of Korea","institution_ids":["https://openalex.org/I104338594"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8085547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"94148","last_page":"94166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8720999956130981,"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":0.8720999956130981,"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":0.023099999874830246,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.00989999994635582,"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/simple","display_name":"Simple (philosophy)","score":0.6802999973297119},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6646999716758728},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6047000288963318},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.47859999537467957},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.41530001163482666},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757099986076355},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6646999716758728},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.47859999537467957},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.41530001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.33379998803138733},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.3124000132083893},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3705442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3705442","pdf_url":null,"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:7889028f233f42dbbf5ea4ce647b7134","is_oa":false,"landing_page_url":"https://doaj.org/article/7889028f233f42dbbf5ea4ce647b7134","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 94148-94166 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3705442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3705442","pdf_url":null,"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":[],"awards":[{"id":"https://openalex.org/G5293985778","display_name":null,"funder_award_id":"SG20240201","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"rise":[2],"of":[3],"Vision-Language":[4],"Models":[5],"(VLMs)":[6],"has":[7],"reframed":[8],"OCR":[9,28,49,133,204,213],"as":[10],"a":[11,104],"generative":[12],"task,":[13],"yet":[14],"deployment":[15],"risk":[16],"is":[17],"not":[18,179],"captured":[19],"by":[20,119],"capped":[21,149],"CER/WER":[22],"alone.":[23],"This":[24],"study":[25],"compares":[26],"nine":[27],"systems":[29],"across":[30],"three":[31,56],"paradigms.":[32],"Seven":[33],"full-suite":[34,165],"systems&#x2014;Tesseract,":[35],"PaddleOCR,":[36],"EasyOCR,":[37],"DeepSeek-OCR-2,":[38],"Chandra,":[39],"Qwen3-VL-8B,":[40],"and":[41,53,55,77,91,114,167,196,220],"InternVL3.5-8B&#x2014;are":[42],"evaluated":[43],"on":[44,175],"4,554":[45],"images":[46],"covering":[47,107],"standard":[48],"conditions":[50],"(ICDAR":[51,82],"2013":[52],"SROIE)":[54],"edge":[57],"cases:":[58],"visual":[59],"degradation":[60],"(IIIT-5K,":[61],"<inline-formula>":[62,71,84,123,159,168],"<tex-math":[63,72,85,124,160,169,207],"notation=\"LaTeX\">$n":[64,73,86],"=":[65,74,87,126],"1$":[66,75,88],"</tex-math></inline-formula>,500),":[67],"layout":[68],"complexity":[69],"(CORD,":[70],"</tex-math></inline-formula>,000),":[76],"visually":[78],"contextual":[79,186],"scene":[80],"text":[81],"2015,":[83],"</tex-math></inline-formula>,475).":[89],"TrOCR":[90],"GOT-OCR2":[92,174],"are":[93],"further":[94],"analyzed":[95],"in":[96],"targeted,":[97],"scope-matched":[98],"experiments.":[99],"Beyond":[100],"CER/WER,":[101],"we":[102],"introduce":[103],"two-tier":[105],"taxonomy":[106],"detection":[108,139],"failure,":[109,140],"recognition":[110],"error,":[111],"over-generation,":[112],"success,":[113],"fine-grained":[115],"hallucination":[116],"labels,":[117],"validated":[118],"dual-coder":[120],"annotation":[121],"(Cohen&#x2019;s":[122],"notation=\"LaTeX\">$\\kappa":[125],"0.681$":[127],"</tex-math></inline-formula>&#x2013;0.900).":[128],"Results":[129],"show":[130],"that":[131],"pipeline":[132,203],"mainly":[134],"fails":[135],"through":[136],"omission":[137],"or":[138],"whereas":[141],"VLMs":[142],"often":[143],"generate":[144],"fluent":[145],"but":[146,188],"unsupported":[147],"text;":[148],"CER":[150],"can":[151],"mask":[152],"this":[153],"risk,":[154],"with":[155],"uncapped/capped":[156],"inflation":[157],"reaching":[158],"notation=\"LaTeX\">$23\\times":[161],"$":[162,171,209],"</tex-math></inline-formula>":[163,172,210],"among":[164],"models":[166],"notation=\"LaTeX\">$107.6\\times":[170],"for":[173],"IIIT-5K.":[176],"H1":[177],"was":[178],"supported:":[180],"VLM":[181],"language":[182],"priors":[183],"aid":[184],"some":[185],"completion":[187],"also":[189],"increase":[190],"hallucination,":[191],"preventing":[192],"consistent":[193],"gains.":[194],"PaddleOCR":[195],"Qwen":[197],"form":[198],"cross-paradigm":[199],"practical":[200],"clusters,":[201],"while":[202],"remains":[205],"10&#x2013;<inline-formula>":[206],"notation=\"LaTeX\">$100\\times":[208],"faster.":[211],"Deployment-oriented":[212],"evaluation":[214],"should":[215],"therefore":[216],"expose":[217],"both":[218],"omission-":[219],"fabrication-dominated":[221],"failures.":[222]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-06-23T00:00:00"}