{"id":"https://openalex.org/W4392402310","doi":"https://doi.org/10.5220/0012416400003660","title":"Detecting Anomalies in Textured Images Using Modified Transformer Masked Autoencoder","display_name":"Detecting Anomalies in Textured Images Using Modified Transformer Masked Autoencoder","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392402310","doi":"https://doi.org/10.5220/0012416400003660"},"language":"en","primary_location":{"id":"doi:10.5220/0012416400003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012416400003660","pdf_url":null,"source":null,"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":"Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012416400003660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069887601","display_name":"Afshin Dini","orcid":"https://orcid.org/0000-0001-6234-3322"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Afshin Dini","raw_affiliation_strings":["Unit of Computing Sciences, Tampere University, Finland, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unit of Computing Sciences, Tampere University, Finland, --- Select a Country ---","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esa Rahtu","raw_affiliation_strings":["Unit of Computing Sciences, Tampere University, Finland, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unit of Computing Sciences, Tampere University, Finland, --- Select a Country ---","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02039133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7569000124931335,"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":0.7569000124931335,"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":0.7236999869346619,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.6510000228881836,"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/autoencoder","display_name":"Autoencoder","score":0.7339255213737488},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5734824538230896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5200259685516357},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45514822006225586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4373374283313751},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41472315788269043},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.3437654376029968},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1364840269088745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11255642771720886},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10592103004455566},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09018495678901672}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7339255213737488},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5734824538230896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5200259685516357},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45514822006225586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4373374283313751},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41472315788269043},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.3437654376029968},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1364840269088745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11255642771720886},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10592103004455566},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09018495678901672}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012416400003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012416400003660","pdf_url":null,"source":null,"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":"Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/210468","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/210468","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":{"id":"doi:10.5220/0012416400003660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012416400003660","pdf_url":null,"source":null,"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":"Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4220775285","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,19,37,105,167,180,201],"new":[3,106],"method":[4,160,199],"for":[5],"detecting":[6],"and":[7,33,46,89,96,111,170,187,206],"locating":[8],"anomalies":[9],"in":[10,48,209],"textured-type":[11],"images":[12,120],"using":[13],"transformer-based":[14],"autoencoders.":[15],"In":[16,78,114],"this":[17,79,131,198],"approach,":[18],"rectangular":[20],"patch":[21],"of":[22,43,83,121,148],"an":[23],"image":[24,95],"is":[25,56,62,158],"masked":[26,76],"by":[27],"setting":[28],"its":[29],"value":[30],"to":[31,50,65,103,109,184,192,204],"gray":[32],"then":[34],"fetched":[35],"into":[36],"pre-trained":[38,60,168],"autoencoder":[39],"with":[40,117],"several":[41],"blocks":[42],"transformer":[44],"encoders":[45],"decoders":[47],"order":[49],"reconstruct":[51,66],"the":[52,59,67,75,81,84,93,97,115,118,122,139,145,152],"unknown":[53],"part.":[54],"It":[55],"shown":[57],"that":[58,127],"model":[61,169],"not":[63,128,156,172],"able":[64],"defective":[68],"parts":[69],"properly":[70],"when":[71],"they":[72],"are":[73],"inside":[74],"patch.":[77],"regard,":[80],"combination":[82],"Structural":[85],"Similarity":[86],"Index":[87],"Measure":[88],"absolute":[90],"error":[91],"between":[92],"reconstructed":[94],"original":[98],"one":[99,195],"can":[100,130,143,196],"be":[101],"used":[102],"define":[104],"anomaly":[107,140],"map":[108,141],"find":[110,133,205],"locate":[112,207],"anomalies.":[113],"experiment":[116],"textured":[119],"MVTec":[123],"dataset,":[124],"we":[125],"discover":[126],"only":[129,157],"approach":[132,203],"anomalous":[134],"samples":[135],"properly,":[136],"but":[137,176],"also":[138,177],"itself":[142],"specify":[144],"exact":[146],"locations":[147],"defects":[149],"correctly":[150],"at":[151],"same":[153],"time.":[154],"Moreover,":[155],"our":[159],"computatio":[161],"nally":[162],"efficient,":[163],"as":[164,200],"it":[165,178],"utilizes":[166],"does":[171],"require":[173],"any":[174],"training,":[175],"has":[179],"better":[181],"performance":[182],"compared":[183],"previous":[185],"autoencoders":[186],"other":[188],"reconstruction-based":[189],"methods.":[190],"Due":[191],"these":[193],"reasons,":[194],"use":[197],"base":[202],"irregularities":[208],"real-world":[210],"applications.":[211]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}