{"id":"https://openalex.org/W3199863078","doi":"https://doi.org/10.1109/tase.2021.3109353","title":"Defect Classification and Detection Using a Multitask Deep One-Class CNN","display_name":"Defect Classification and Detection Using a Multitask Deep One-Class CNN","publication_year":2021,"publication_date":"2021-09-14","ids":{"openalex":"https://openalex.org/W3199863078","doi":"https://doi.org/10.1109/tase.2021.3109353","mag":"3199863078"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2021.3109353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2021.3109353","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","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/A5026151886","display_name":"Xinghui Dong","orcid":"https://orcid.org/0000-0003-1047-427X"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Xinghui Dong","raw_affiliation_strings":["Centre for Imaging Sciences, The University of Manchester, Manchester, U.K","School of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Centre for Imaging Sciences, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"School of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067224766","display_name":"Chris Taylor","orcid":"https://orcid.org/0000-0001-7867-9533"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher J. Taylor","raw_affiliation_strings":["Centre for Imaging Sciences, The University of Manchester, Manchester, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Imaging Sciences, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058456050","display_name":"T.F. Cootes","orcid":"https://orcid.org/0000-0002-2695-9063"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim F. Cootes","raw_affiliation_strings":["Centre for Imaging Sciences, The University of Manchester, Manchester, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Imaging Sciences, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026151886"],"corresponding_institution_ids":["https://openalex.org/I28407311","https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":4.8985,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95907848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"19","issue":"3","first_page":"1719","last_page":"1730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9951000213623047,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9933000206947327,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/autoencoder","display_name":"Autoencoder","score":0.826949954032898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8133506774902344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526292204856873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7334680557250977},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6316084861755371},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6277633905410767},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6129076480865479},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5382350087165833},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5165085196495056},{"id":"https://openalex.org/keywords/hypersphere","display_name":"Hypersphere","score":0.500363826751709},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45536842942237854},{"id":"https://openalex.org/keywords/one-class-classification","display_name":"One-class classification","score":0.44451767206192017},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.4297376275062561},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42796817421913147},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34892112016677856},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08394366502761841}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.826949954032898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8133506774902344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526292204856873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7334680557250977},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6316084861755371},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6277633905410767},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6129076480865479},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5382350087165833},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5165085196495056},{"id":"https://openalex.org/C2776562905","wikidata":"https://www.wikidata.org/wiki/Q306610","display_name":"Hypersphere","level":2,"score":0.500363826751709},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45536842942237854},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.44451767206192017},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.4297376275062561},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42796817421913147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34892112016677856},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08394366502761841},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tase.2021.3109353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2021.3109353","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/41486b01-cad3-4101-9c12-c76fef30cd8a","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/41486b01-cad3-4101-9c12-c76fef30cd8a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dong, X, Taylor, C & Cootes, T 2022, 'Defect Classification and Detection Using a Multitask Deep One-Class CNN', IEEE Transactions on Automation Science and Engineering, vol. 19, no. 3, pp. 1719-1730. https://doi.org/10.1109/TASE.2021.3109353","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4959847549","display_name":"UK RESEARCH CENTRE IN NON-DESTRUCTIVE EVALUATION (RCNDE) 2014-2020","funder_award_id":"EP/L022125/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7571721515","display_name":null,"funder_award_id":"EP/L022125/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W6770282","https://openalex.org/W1562291184","https://openalex.org/W1876967670","https://openalex.org/W1901129140","https://openalex.org/W2014774208","https://openalex.org/W2022686119","https://openalex.org/W2047859144","https://openalex.org/W2132870739","https://openalex.org/W2147800946","https://openalex.org/W2152575748","https://openalex.org/W2163605009","https://openalex.org/W2340896621","https://openalex.org/W2502312327","https://openalex.org/W2559966763","https://openalex.org/W2599354622","https://openalex.org/W2621614835","https://openalex.org/W2625100732","https://openalex.org/W2764067741","https://openalex.org/W2783748519","https://openalex.org/W2803697594","https://openalex.org/W2899750794","https://openalex.org/W2903557259","https://openalex.org/W2905065306","https://openalex.org/W2905867642","https://openalex.org/W2911964244","https://openalex.org/W2914478989","https://openalex.org/W2919115771","https://openalex.org/W2948982773","https://openalex.org/W2962974533","https://openalex.org/W2963173190","https://openalex.org/W2963446712","https://openalex.org/W2963541464","https://openalex.org/W2964236768","https://openalex.org/W2982781781","https://openalex.org/W3085046840","https://openalex.org/W3094625083","https://openalex.org/W3098401985","https://openalex.org/W3105939760","https://openalex.org/W3110667462","https://openalex.org/W3136545562","https://openalex.org/W4297803714","https://openalex.org/W6600271633","https://openalex.org/W6639824700","https://openalex.org/W6684191040","https://openalex.org/W6724804524","https://openalex.org/W6751494907"],"related_works":["https://openalex.org/W4287995534","https://openalex.org/W2998168123","https://openalex.org/W2772780115","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W2592385986","https://openalex.org/W2742991909","https://openalex.org/W3156786002","https://openalex.org/W2292254049","https://openalex.org/W2772371429"],"abstract_inverted_index":{"Defect":[0],"classification":[1,72,119,296],"and":[2,21,47,51,81,137,152,172,252],"detection":[3,186,306],"have":[4],"been":[5],"explored":[6],"using":[7,126,189,211,231,322],"convolutional":[8,286],"neural":[9,287],"networks":[10],"(CNNs).":[11],"Normally,":[12],"a":[13,33,61,89,105,124,143,156,190,212,275,285,327,360],"large":[14,34],"set":[15,35,328],"of":[16,36,114,175,196,243,262,313,329],"training":[17,284],"images":[18,37,80,282,339],"containing":[19],"defects":[20,44],"the":[22,110,135,138,150,166,173,176,181,197,226,237,241,302,332,352,363,367],"associated":[23],"annotation":[24,48],"data":[25,83],"are":[26,45,347,375],"required":[27],"by":[28,366],"these":[29,55],"approaches.":[30,356],"However,":[31],"such":[32],"is":[38,49,102,130,160,178,187],"usually":[39],"difficult":[40],"to":[41,59,132,142,240,249,270,292,304,326,362,377],"collect":[42],"because":[43],"rare":[46],"time-consuming":[50],"expensive.":[52],"To":[53,147],"address":[54],"issues,":[56],"we":[57,87],"propose":[58],"use":[60,337],"multitask":[62,115,157,244],"deep":[63,144,198],"one-class":[64,118,145,153,199,294],"CNN":[65,75,355],"for":[66,84,93,283,340],"defect":[67,185,216,295,305],"classification.":[68],"Compared":[69],"with":[70,307],"supervised":[71,227,353],"methods,":[73],"this":[74],"does":[76,278,335],"not":[77,267,279,336],"require":[78,259,280],"abnormal":[79,263,281,338,373],"annotated":[82,233],"training.":[85],"Specifically,":[86],"build":[88],"stacked":[90],"encoder\u2013decoder":[91],"autoencoder":[92,151],"learning":[94],"feature":[95,106,170],"representation":[96,171],"from":[97],"normal":[98],"images.":[99],"The":[100,201],"encoder":[101,136],"used":[103,179],"as":[104,123,180,223,225,349,351],"extractor":[107],"based":[108],"on":[109,194],"hard":[111,376],"sharing":[112],"scheme":[113],"learning.":[116,245],"A":[117],"(OCC)":[120],"objective":[121,140],"learned":[122],"hypersphere":[125,177],"minimum":[127],"volume":[128],"estimation":[129],"appended":[131],"it.":[133],"Together":[134],"OCC":[139],"lead":[141],"classifier.":[146,200],"train":[148],"both":[149],"classifier":[154],"end-to-end,":[155],"loss":[158],"function":[159],"built.":[161],"Given":[162],"an":[163],"unknown":[164],"sample,":[165],"distance":[167],"between":[168],"its":[169,208],"center":[174],"anomaly":[182],"score.":[183],"Furthermore,":[184],"implemented":[188],"moving-window":[191],"scanning":[192],"method":[193,228,276,303,324,334],"top":[195],"proposed":[202,333],"approach":[203,219],"achieves":[204,220],"better":[205,317],"performance":[206,318],"than":[207],"counterparts":[209],"trained":[210],"two-stage":[213],"method.":[214],"For":[215],"detection,":[217],"our":[218,323],"results":[221,239,312,345],"almost":[222,348],"good":[224,350],"even":[229],"without":[230],"any":[232],"data.":[234],"We":[235,299,310],"attribute":[236],"promising":[238,308],"advantages":[242],"<italic":[246],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[247],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Note":[248],"Practitioners</i>":[250],"\u2014Building":[251],"evaluating":[253],"vision-based":[254],"nondestructive":[255],"testing":[256],"(NDT)":[257],"techniques":[258],"many":[260],"examples":[261],"images,":[264],"which":[265],"may":[266],"be":[268,320],"easy":[269],"acquire.":[271],"This":[272,357],"article":[273],"describes":[274],"that":[277,316,346],"network":[288],"(CNN)":[289],"in":[290],"order":[291],"perform":[293],"(outlier":[297],"detection).":[298],"also":[300],"applied":[301],"results.":[309],"include":[311],"experiments":[314],"demonstrating":[315],"can":[319],"obtained":[321],"compared":[325],"baselines.":[330],"Although":[331],"training,":[341],"it":[342],"still":[343],"produces":[344],"learning-based":[354],"study":[358],"provides":[359],"solution":[361],"challenge":[364],"encountered":[365],"industrial":[368],"inspection":[369],"community":[370],"when":[371],"enough":[372],"samples":[374],"obtain.":[378]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}