{"id":"https://openalex.org/W4394938872","doi":"https://doi.org/10.1109/jiot.2024.3390700","title":"OCR-Diff: A Two-Stage Deep Learning Framework for Optical Character Recognition Using Diffusion Model in Industrial Internet of Things","display_name":"OCR-Diff: A Two-Stage Deep Learning Framework for Optical Character Recognition Using Diffusion Model in Industrial Internet of Things","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4394938872","doi":"https://doi.org/10.1109/jiot.2024.3390700"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2024.3390700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3390700","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","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/A5102011933","display_name":"Chaewon Park","orcid":"https://orcid.org/0009-0009-9378-381X"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chae-Won Park","raw_affiliation_strings":["Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009301325","display_name":"Vikas Palakonda","orcid":"https://orcid.org/0009-0001-6390-2373"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Vikas Palakonda","raw_affiliation_strings":["Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081379260","display_name":"Sangseok Yun","orcid":"https://orcid.org/0000-0002-7961-1394"},"institutions":[{"id":"https://openalex.org/I8991828","display_name":"Pukyong National University","ror":"https://ror.org/0433kqc49","country_code":"KR","type":"education","lineage":["https://openalex.org/I8991828"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangseok Yun","raw_affiliation_strings":["Department of Information and Communications Engineering, Pukyong National University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7961-1394","affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering, Pukyong National University, Busan, South Korea","institution_ids":["https://openalex.org/I8991828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045676802","display_name":"Il\u2010Min Kim","orcid":"https://orcid.org/0000-0003-1339-8057"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Il-Min Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Queen’s University, Kingston, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1339-8057","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Queen’s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028237781","display_name":"Jae\u2010Mo Kang","orcid":"https://orcid.org/0000-0002-8181-5994"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Mo Kang","raw_affiliation_strings":["Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8181-5994","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Kyungpook National University, Daegu, South Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6162,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91046466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":"15","first_page":"25997","last_page":"26000"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9952999949455261,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9936000108718872,"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":0.8599730730056763},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6759409308433533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6058204174041748},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6015645265579224},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5937912464141846},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5385180115699768},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.532181978225708},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5284613966941833},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.47940513491630554},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47937753796577454},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4690948724746704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4297497570514679},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.429684579372406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3616575300693512},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3229139447212219},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24757719039916992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8599730730056763},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6759409308433533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6058204174041748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6015645265579224},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5937912464141846},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5385180115699768},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.532181978225708},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5284613966941833},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.47940513491630554},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47937753796577454},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4690948724746704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4297497570514679},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.429684579372406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3616575300693512},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3229139447212219},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24757719039916992},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2024.3390700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3390700","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4501936101","display_name":null,"funder_award_id":"IITP-2024-2020- 0-01808","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7392775442","display_name":null,"funder_award_id":"2022R1A4A1033830","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W54257720","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2810983211","https://openalex.org/W2963470893","https://openalex.org/W2963526661","https://openalex.org/W3045923047","https://openalex.org/W3107840264","https://openalex.org/W3155072588","https://openalex.org/W3175528029","https://openalex.org/W3177505580","https://openalex.org/W4226014430","https://openalex.org/W4312419898","https://openalex.org/W4360995272","https://openalex.org/W4385245566","https://openalex.org/W4386410320","https://openalex.org/W6779823529","https://openalex.org/W6781138733","https://openalex.org/W6788990321","https://openalex.org/W6797359156"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W3082848404","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2],"(OCR)":[3],"is":[4,24,65,89],"one":[5],"of":[6,75,84,133],"the":[7,58,73,76,82,92,97,100,118,121,129,134],"key":[8],"enabling":[9],"technologies":[10],"in":[11,37,120],"industrial":[12],"internet-of-things":[13],"(IIoT)":[14],"for":[15,48,110],"extracting":[16],"and":[17,104,131],"utilizing":[18],"useful":[19],"textual":[20],"information,":[21],"but":[22],"it":[23],"technically":[25],"challenging":[26],"due":[27],"to":[28,115],"poor":[29],"environmental":[30],"conditions.":[31],"To":[32],"deal":[33],"with":[34,68,72],"such":[35,80],"challenges,":[36],"this":[38],"letter,":[39],"we":[40],"propose":[41],"a":[42,51,69,85],"novel":[43],"two-stage":[44],"deep":[45],"learning":[46],"framework":[47],"OCR":[49],"using":[50],"generative":[52],"diffusion":[53,78,94],"model,":[54],"namely,":[55],"OCR-Diff.":[56],"In":[57,96],"first":[59],"stage,":[60,99],"our":[61],"customized":[62],"conditional":[63,102],"U-Net":[64,103],"pre-trained":[66,101],"jointly":[67,108],"feature":[70,105],"extractor":[71,106],"aid":[74],"forward":[77],"process":[79],"that":[81],"quality":[83],"low-resolution":[86],"text":[87,113],"image":[88],"improved":[90],"via":[91],"reverse":[93],"process.":[95],"next":[98],"are":[107],"fine-tuned":[109],"an":[111],"off-the-shelf":[112],"recognizer":[114],"precisely":[116],"recognize":[117],"texts":[119],"image.":[122],"Experimental":[123],"results":[124],"on":[125],"TextZoom":[126],"datasets":[127],"substantiate":[128],"superiority":[130],"effectiveness":[132],"proposed":[135],"scheme.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}