{"id":"https://openalex.org/W4405845276","doi":"https://doi.org/10.1109/apccas62602.2024.10808400","title":"OCR is All you need: Importing Multi-Modality into Image-based Defect Classification System","display_name":"OCR is All you need: Importing Multi-Modality into Image-based Defect Classification System","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405845276","doi":"https://doi.org/10.1109/apccas62602.2024.10808400"},"language":"en","primary_location":{"id":"doi:10.1109/apccas62602.2024.10808400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas62602.2024.10808400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5007305393","display_name":"Chih\u2013Chung Hsu","orcid":"https://orcid.org/0000-0002-2083-4438"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Chung Hsu","raw_affiliation_strings":["Institute of Data Science National Cheng Kung University,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034075233","display_name":"Chia-Ming Lee","orcid":"https://orcid.org/0009-0004-6027-3083"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ming Lee","raw_affiliation_strings":["Institute of Data Science National Cheng Kung University,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042865958","display_name":"Peng Yu","orcid":"https://orcid.org/0000-0002-6831-4685"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Tsun Yu","raw_affiliation_strings":["Institute of Data Science National Cheng Kung University,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science National Cheng Kung University,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104278307","display_name":"Chun-Hung Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2799432993","display_name":"Advanced Semiconductor Engineering (Taiwan)","ror":"https://ror.org/04rgfzt17","country_code":"TW","type":"company","lineage":["https://openalex.org/I2799432993"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Hung Sun","raw_affiliation_strings":["Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan","institution_ids":["https://openalex.org/I2799432993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036470676","display_name":"Kuang\u2010Ming Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2799432993","display_name":"Advanced Semiconductor Engineering (Taiwan)","ror":"https://ror.org/04rgfzt17","country_code":"TW","type":"company","lineage":["https://openalex.org/I2799432993"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuang-Ming Wu","raw_affiliation_strings":["Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate R&D Advanced Semiconductor Engineering Group,Kaoshuing,Taiwan","institution_ids":["https://openalex.org/I2799432993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3052,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66128994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9821000099182129,"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":0.9621000289916992,"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":0.7322065830230713},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6785123348236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5708572864532471},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5039991736412048},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4418063759803772},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43369171023368835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4267526865005493},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.347289115190506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322065830230713},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6785123348236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708572864532471},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5039991736412048},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4418063759803772},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43369171023368835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4267526865005493},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.347289115190506}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas62602.2024.10808400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas62602.2024.10808400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324663","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2519818067","https://openalex.org/W2605076167","https://openalex.org/W2923486253","https://openalex.org/W3109969984","https://openalex.org/W4308235797","https://openalex.org/W4318718936","https://openalex.org/W6637373629","https://openalex.org/W6679436768","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6750729320","https://openalex.org/W6762718338","https://openalex.org/W6772833837","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W2546503577"],"abstract_inverted_index":{"Automatic":[0],"optical":[1,74],"inspection":[2],"(AOI)":[3],"plays":[4],"a":[5,47,84,109,119],"pivotal":[6],"role":[7],"in":[8,73,122,153],"the":[9,22,100,127,145],"manufacturing":[10],"process.":[11],"It":[12],"detects":[13],"anomalies":[14],"by":[15],"analyzing":[16],"image":[17],"patterns.":[18],"Despite":[19],"its":[20],"importance,":[21],"deployment":[23],"of":[24,96,129],"models":[25],"for":[26],"AOI":[27,42,59],"often":[28,43],"faces":[29],"challenges.":[30],"These":[31],"include":[32],"limited":[33],"sample":[34],"sizes,":[35],"variations":[36],"among":[37],"dataset,":[38],"and":[39,118,134,149],"camera-poses.":[40],"Besides,":[41],"fails":[44],"to":[45,78,87,125],"capture":[46],"rich":[48],"mechanism-parameter":[49],"information":[50],"from":[51,81],"machines":[52],"or":[53],"inside":[54],"images,":[55],"which":[56],"typically":[57],"benefit":[58],"classification.":[60],"To":[61],"address":[62],"this,":[63],"we":[64],"introduce":[65,115],"an":[66],"external":[67,85],"modality-guided":[68],"defect":[69,146],"classification":[70,147],"framework,":[71],"rooted":[72],"character":[75],"recognition":[76],"(OCR),":[77],"extract":[79],"features":[80],"images":[82],"as":[83],"modality":[86,105],"enhance":[88],"performance,":[89],"termed":[90],"OANet":[91,124],"(Ocr-Aoi-Net).":[92],"A":[93],"key":[94],"aspect":[95],"our":[97,123,141],"approach":[98],"is":[99],"feature":[101,116],"alignment":[102],"between":[103],"differemt":[104],"features,":[106,131],"extracted":[107],"using":[108],"single":[110],"modality-aware":[111],"model.":[112],"We":[113],"further":[114],"refinement":[117],"gating":[120],"function":[121],"optimize":[126],"combination":[128],"these":[130],"enhancing":[132],"inference":[133],"decision-making":[135],"capabilities.":[136],"Experimental":[137],"outcomes":[138],"show":[139],"that":[140],"methodology":[142],"considerably":[143],"imporoved":[144],"model":[148],"maintains":[150],"robustness":[151],"even":[152],"challenging":[154],"scenarios.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}