{"id":"https://openalex.org/W7130833320","doi":"https://doi.org/10.1007/s44196-026-01197-z","title":"Visual Weld Quality Inspection System for Identifying Defects in GMAW Joints with Semantic Segmentation on Pre-trained Models","display_name":"Visual Weld Quality Inspection System for Identifying Defects in GMAW Joints with Semantic Segmentation on Pre-trained Models","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7130833320","doi":"https://doi.org/10.1007/s44196-026-01197-z"},"language":"en","primary_location":{"id":"doi:10.1007/s44196-026-01197-z","doi":"https://doi.org/10.1007/s44196-026-01197-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-026-01197-z","pdf_url":null,"source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44196-026-01197-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126550688","display_name":"Melitsa Torres-Torres","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universitat Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Melitsa Torres-Torres","raw_affiliation_strings":["Department d\u2019Enginyeria Inform\u00e0tica i Matem\u00e0tiques, Universitat Rovira i Virgili, 43007, Tarragona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department d\u2019Enginyeria Inform\u00e0tica i Matem\u00e0tiques, Universitat Rovira i Virgili, 43007, Tarragona, Spain","institution_ids":["https://openalex.org/I55952717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126543042","display_name":"Kevin Velasquez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Velasquez","raw_affiliation_strings":["G5ID Research Group, Oniris ID, Barranquilla, 080020, Colombia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"G5ID Research Group, Oniris ID, Barranquilla, 080020, Colombia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112598587","display_name":"Jos\u00e9 E. Guti\u00e9rrez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112678","display_name":"University of the Coast","ror":"https://ror.org/01v5nhr20","country_code":"CO","type":"education","lineage":["https://openalex.org/I4210112678"]}],"countries":["CO"],"is_corresponding":true,"raw_author_name":"Jos\u00e9 Escorcia-Gutierrez","raw_affiliation_strings":["Department of Computational Science and Electronics, Universidad de la Costa, CUC, Barranquilla, 080020, Colombia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Science and Electronics, Universidad de la Costa, CUC, Barranquilla, 080020, Colombia","institution_ids":["https://openalex.org/I4210112678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025525181","display_name":"A\u0131\u0308da Valls","orcid":"https://orcid.org/0000-0003-3616-7809","observed_orcids":["https://orcid.org/0000-0003-3616-7809"]},"institutions":[{"id":"https://openalex.org/I55952717","display_name":"Universitat Rovira i Virgili","ror":"https://ror.org/00g5sqv46","country_code":"ES","type":"education","lineage":["https://openalex.org/I55952717"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Aida Valls","raw_affiliation_strings":["Center of Environmental, Food and Toxicological Technology - TecnATox, Universitat Rovira i Virgili, 43201, Reus, Spain","Department d\u2019Enginyeria Inform\u00e0tica i Matem\u00e0tiques, Universitat Rovira i Virgili, 43007, Tarragona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Environmental, Food and Toxicological Technology - TecnATox, Universitat Rovira i Virgili, 43201, Reus, Spain","institution_ids":["https://openalex.org/I55952717"]},{"raw_affiliation_string":"Department d\u2019Enginyeria Inform\u00e0tica i Matem\u00e0tiques, Universitat Rovira i Virgili, 43007, Tarragona, Spain","institution_ids":["https://openalex.org/I55952717"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025525181","https://openalex.org/A5112598587"],"corresponding_institution_ids":["https://openalex.org/I4210112678","https://openalex.org/I55952717"],"apc_list":{"value":2490,"currency":"USD","value_usd":2490},"apc_paid":{"value":2490,"currency":"USD","value_usd":2490},"fwci":16.6031,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98922493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"19","issue":"1","first_page":null,"last_page":null},"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":0.9970999956130981,"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":0.9970999956130981,"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/T12169","display_name":"Non-Destructive Testing Techniques","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gas-metal-arc-welding","display_name":"gas metal arc welding","score":0.8830000162124634},{"id":"https://openalex.org/keywords/weld-defect-detection","display_name":"weld defect detection","score":0.8920000195503235},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.8040000200271606},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.6650000214576721},{"id":"https://openalex.org/keywords/pre-trained-convolutional-neural-networks","display_name":"pre-trained convolutional neural networks","score":0.8709999918937683},{"id":"https://openalex.org/keywords/stainless-steel-welds","display_name":"stainless steel welds","score":0.6520000100135803},{"id":"https://openalex.org/keywords/lack-of-penetration","display_name":"lack of penetration","score":0.8029999732971191},{"id":"https://openalex.org/keywords/spatter","display_name":"spatter","score":0.972000002861023},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.6880000233650208},{"id":"https://openalex.org/keywords/linknet","display_name":"LinkNet","score":0.9739999771118164},{"id":"https://openalex.org/keywords/feature-pyramid-network","display_name":"feature pyramid network","score":0.9819999933242798},{"id":"https://openalex.org/keywords/automated-visual-inspection","display_name":"automated visual inspection","score":0.6800000071525574},{"id":"https://openalex.org/keywords/welding-quality-assurance","display_name":"welding quality assurance","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7023000121116638},{"id":"https://openalex.org/C19474535","wikidata":"https://www.wikidata.org/wiki/Q131172","display_name":"Welding","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C50916996","wikidata":"https://www.wikidata.org/wiki/Q1765723","display_name":"Gas metal arc welding","level":4,"score":0.4447000026702881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C3450827","wikidata":"https://www.wikidata.org/wiki/Q1627310","display_name":"Gas tungsten arc welding","level":4,"score":0.3783999979496002},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2776143536","wikidata":"https://www.wikidata.org/wiki/Q7980866","display_name":"Weld pool","level":5,"score":0.3393000066280365},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C118198166","wikidata":"https://www.wikidata.org/wiki/Q2327264","display_name":"Robot welding","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C20480867","wikidata":"https://www.wikidata.org/wiki/Q422937","display_name":"Arc welding","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44196-026-01197-z","doi":"https://doi.org/10.1007/s44196-026-01197-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-026-01197-z","pdf_url":null,"source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3b83bcc28dec462ca8318beb2f3a3212","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/3b83bcc28dec462ca8318beb2f3a3212","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,"listed_in":[],"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":"International Journal of Computational Intelligence Systems, Vol 19, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44196-026-01197-z","doi":"https://doi.org/10.1007/s44196-026-01197-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-026-01197-z","pdf_url":null,"source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.7207000255584717}],"sustainable_development_goals_aurora":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6802407503128052}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1673306728","display_name":null,"funder_award_id":"2021 SGR 00114","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G4874923377","display_name":null,"funder_award_id":"2023PFR-URV-114","funder_id":"https://openalex.org/F4320324497","funder_display_name":"Universitat Rovira i Virgili"}],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320324497","display_name":"Universitat Rovira i Virgili","ror":"https://ror.org/00g5sqv46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1976468890","https://openalex.org/W2030877626","https://openalex.org/W2112796928","https://openalex.org/W2132763323","https://openalex.org/W2153207353","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2254884657","https://openalex.org/W2400231982","https://openalex.org/W2565639579","https://openalex.org/W2735039185","https://openalex.org/W2804860796","https://openalex.org/W2884561390","https://openalex.org/W2889985731","https://openalex.org/W2941542910","https://openalex.org/W2945708832","https://openalex.org/W2946433709","https://openalex.org/W2960155470","https://openalex.org/W2964350391","https://openalex.org/W2968982355","https://openalex.org/W2969856252","https://openalex.org/W2973272210","https://openalex.org/W2995385467","https://openalex.org/W2996102538","https://openalex.org/W3005892455","https://openalex.org/W3027554678","https://openalex.org/W3033221398","https://openalex.org/W3040156639","https://openalex.org/W3041528150","https://openalex.org/W3082329034","https://openalex.org/W3132064345","https://openalex.org/W3159315196","https://openalex.org/W3198632068","https://openalex.org/W4200333963","https://openalex.org/W4309709978","https://openalex.org/W4327606547","https://openalex.org/W4367845370","https://openalex.org/W4378975002","https://openalex.org/W4387462831","https://openalex.org/W4392936874","https://openalex.org/W4399198991","https://openalex.org/W4402278112","https://openalex.org/W4403906541","https://openalex.org/W4411990295"],"related_works":[],"abstract_inverted_index":{"Gas":[0],"metal":[1,11],"arc":[2],"welds":[3,52],"are":[4,24],"used":[5,41],"in":[6,26,35,66,287,343],"industrial":[7],"manufacturing":[8,353],"for":[9,42,235,339],"joining":[10],"components":[12],"due":[13,162],"to":[14,59,92,150,159,163,200,348],"their":[15],"high":[16],"deposition":[17],"rates,":[18],"versatility,":[19],"and":[20,33,63,76,94,106,121,131,153,188,220,251,263,280,297,305,311,326,359],"cost-effectiveness.":[21],"These":[22,329],"processes":[23],"fundamental":[25],"sectors":[27],"such":[28],"as":[29,55,265,323],"automotive,":[30],"aerospace,":[31],"construction,":[32],"notably,":[34],"the":[36,47,77,164,186,192,214,277,281,309,332,349],"fabrication":[37],"of":[38,49,101,108,171,175,191,204,210,216,295,299,303,307,334,351],"tubular":[39,51],"joints":[40],"natural":[43],"gas":[44,67],"pipelines.":[45],"Ensuring":[46],"integrity":[48],"these":[50],"is":[53,169],"critical,":[54],"defects":[56,99,206],"can":[57],"lead":[58],"leaks,":[60],"safety":[61],"hazards,":[62],"costly":[64],"failures":[65],"pipeline":[68,140],"infrastructure,":[69],"which":[70,168],"may":[71],"affect":[72],"both":[73,185],"human":[74],"health":[75],"environment.":[78],"This":[79],"research":[80],"proposes":[81],"an":[82,293],"intelligent":[83],"visual":[84,218,232,337],"inspection":[85,338],"system":[86],"based":[87],"on":[88,207],"convolutional":[89,228],"neural":[90],"networks":[91],"detect":[93],"classify":[95],"four":[96,114],"critical":[97,234],"welding":[98,178,205,211,344],"(lack":[100],"continuity,":[102,308],"excess":[103],"penetration,":[104],"spatter,":[105],"lack":[107,302,306],"penetration)":[109],"through":[110],"transfer":[111],"learning":[112],"with":[113,141,243,276,319,356],"pre-trained":[115,227],"models":[116,248,315],"(i.e.,":[117],"VGG-16,":[118],"ResNet-101,":[119],"EfficientNetB3,":[120],"Inception-ResNet-v2),":[122],"integrated":[123],"into":[124],"three":[125],"semantic":[126],"segmentation":[127,197,241],"architectures:":[128],"U-Net;":[129],"LinkNet,":[130,272],"Feature":[132,222,312],"pyramid":[133,313],"network.":[134],"The":[135,247,268],"methodology":[136],"includes:":[137],"(i)":[138],"Preprocessing":[139],"image":[142],"enhancement":[143,149],"techniques":[144,156],"applying":[145],"contrast":[146,152],"equalization":[147],"technique":[148],"improve":[151],"data":[154],"augmentation":[155],"were":[157,249],"employed":[158,199],"mitigate":[160],"overfitting":[161],"limited":[165],"dataset":[166],"size;":[167],"composed":[170],"220":[172],"high-resolution":[173],"images":[174,209],"stainless":[176],"steel":[177],"process":[179,345],"created":[180],"under":[181],"controlled":[182],"conditions,":[183],"capturing":[184,230],"top":[187],"root":[189],"sides":[190],"weld":[193,238],"beads;":[194],"(ii)":[195],"Semantic":[196],"was":[198,224],"perform":[201],"pixel-wise":[202],"classification":[203],"visible-spectrum":[208],"joints,":[212],"enhancing":[213],"accuracy":[215,242],"automated":[217],"inspection;":[219],"iii)":[221],"extraction":[223],"conducted":[225],"using":[226,256],"backbones,":[229],"hierarchical":[231],"patterns":[233],"identifying":[236],"subtle":[237],"defects,":[239,291],"improving":[240,340],"reduced":[244],"training":[245],"data.":[246],"trained":[250],"evaluated":[252],"across":[253],"96":[254],"configurations":[255],"accuracy,":[257],"Jaccard":[258],"index,":[259],"F1-score,":[260],"precision,":[261],"sensitivity,":[262],"specificity":[264,298],"evaluation":[266],"metrics.":[267],"results":[269],"demonstrated":[270],"that":[271],"particularly":[273],"when":[274],"combined":[275],"EfficientNetB3":[278,320],"backbone":[279],"RMSprop":[282],"optimizer,":[283],"provided":[284],"superior":[285],"performance":[286],"segmenting":[288],"exceed":[289],"penetration":[290,304],"achieving":[292],"F1-score":[294],"92.3%":[296],"89.5%.":[300],"For":[301],"U-Net":[310],"network":[314],"showed":[316],"competitive":[317],"performance,":[318],"again":[321],"emerging":[322],"a":[324],"robust":[325],"efficient":[327],"backbone.":[328],"findings":[330],"highlight":[331],"potential":[333],"deep":[335],"learning-driven":[336],"quality":[341],"assurance":[342],"applications,":[346],"contributing":[347],"development":[350,361],"smart":[352],"systems":[354],"aligned":[355],"Industry":[357],"4.0":[358],"sustainable":[360],"objectives.":[362]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-02-22T00:00:00"}