{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:05:47Z","timestamp":1773047147027,"version":"3.50.1"},"reference-count":37,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":67,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Defect detection in fused filament fabrication (FFF) is essential to ensuring part reliability, as printing faults such as layer shift, under\u2010extrusion, and poor adhesion can compromise structural integrity and increase material waste. However, existing monitoring approaches often lack the spatial resolution or robustness needed for real\u2010time, layer\u2010wise assessment. This study addresses this gap by investigating whether high\u2010resolution, full\u2010reference feature comparison can reliably detect catastrophic defects during printing. We propose a real\u2010time monitoring framework that captures 720 \u00d7 1,280 images of each printed layer using an onboard monocular camera and compares them with either simulated reference layers\u2014generated from G\u2010code using a calibrated Blender environment\u2014or reference images from a defect\u2010free print. Multi\u2010resolution embeddings extracted from three intermediate layers of a modified ResNet50 are compared using L2 feature\u2010space distance to localise anomalous regions. Across 24 experimental prints containing four major defect classes, the system achieved 100% detection of catastrophic defects with zero false positives under the tested conditions, while processing each layer in &lt;2 s on a standard CPU. Limitations include camera blind spots, lighting sensitivity during early layers, and appearance mismatches in simulated references due to unmodelled thermal effects. Future work will incorporate thermo\u2010mechanical simulation, multi\u2010camera configurations, and real\u2010time corrective feedback. The proposed method provides a practical and efficient foundation for industrial FFF quality assurance and automated, in\u2010situ defect detection.<\/jats:p>","DOI":"10.1049\/ipr2.70281","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:09:23Z","timestamp":1773043763000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Defect Detection in Fused Filament 3D Printing, Using Embedding Similarity"],"prefix":"10.1049","volume":"20","author":[{"given":"Saleh","family":"Ebrahimian","sequence":"first","affiliation":[{"name":"AI\u2010innovate Solutions Inc.  Oakville Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elham","family":"Armin","sequence":"additional","affiliation":[{"name":"AI\u2010innovate Solutions Inc.  Oakville Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanstantsin","family":"Pachkouski","sequence":"additional","affiliation":[{"name":"Mosaic Manufacturing Ltd.  Toronto Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Drew","family":"Shark","sequence":"additional","affiliation":[{"name":"Matter and Form Inc.  Toronto Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Tucker","sequence":"additional","affiliation":[{"name":"Mosaic Manufacturing Ltd.  Toronto Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kysen","family":"Leo","sequence":"additional","affiliation":[{"name":"Mosaic Manufacturing Ltd.  Toronto Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Sanjari","sequence":"additional","affiliation":[{"name":"AI\u2010innovate Solutions Inc.  Oakville Ontario Canada"},{"name":"SAIWA Inc. Burlington Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peyman","family":"Saidi","sequence":"additional","affiliation":[{"name":"Queen's University  Kingston Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3560-8070","authenticated-orcid":false,"given":"Hamid\u2010Reza","family":"Pourreza","sequence":"additional","affiliation":[{"name":"AI\u2010innovate Solutions Inc.  Oakville Ontario Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170\u2010024\u201013269\u20105"},{"key":"e_1_2_11_3_1","volume-title":"Printing and Additive Manufacturing: Principles and Applications\u2010of Rapid Prototyping","author":"Chua C. K.","year":"2016"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsbiomaterials.0c01761"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2020.101473"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2022.102690"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2020.101749"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2023.103409"},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"J.Yan S.Bai Y.Li X.Yu andC.Cai \u201cA Wire Drawing Defect Detection Approach for FDM 3D Printing Based on Machine Vision Technology \u201d inInternational Conference on Artificial Intelligence and Computer Applications(IEEE 2023) 1\u2013477 https:\/\/doi.org\/10.1109\/ICAICA58456.2023.10405405.","DOI":"10.1109\/ICAICA58456.2023.10405405"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.12.315"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40964\u2010021\u201000192\u20104"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170\u2010025\u201016382\u20101"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/machines3020055"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170\u2010020\u201006241\u20106"},{"key":"e_1_2_11_15_1","doi-asserted-by":"crossref","unstructured":"M. S.Khandpur M.Galati P.Minetola G.Marchiandi L.Fontana andV.Stiuso \u201cDevelopment of a Low\u2010Cost Monitoring System for Open 3 D Printing \u201d inIOP Conference Series: Materials Science and Engineering(IOP Publishing 2021) 012044 https:\/\/doi.org\/10.1088\/1757\u2010899X\/1136\/1\/012044.","DOI":"10.1088\/1757-899X\/1136\/1\/012044"},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","unstructured":"Y.Niu E.Chadwick A. W.Ma andQ.Yang \u201cSemi\u2010Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing \u201d prepirint arXiv December 16 2023 https:\/\/doi.org\/10.48550\/arXiv.2212.08583.","DOI":"10.1007\/978-3-031-44137-0_16"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/jmmp9030074"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"F.BaumannandD.Roller \u201cVision Based Error Detection for 3D Printing Processes \u201d inProceedings of the MATEC Web of Conferences. EDP Sciences(EDP Sciences 2016) 06003 https:\/\/doi.org\/10.1051\/matecconf\/20165906003.","DOI":"10.1051\/matecconf\/20165906003"},{"key":"e_1_2_11_19_1","doi-asserted-by":"crossref","unstructured":"J.Yan S.Bai Y.Li X.Yu andC.Cai \u201cA Wire Drawing Defect Detection Approach for FDM 3D Printing Based on Machine Vision Technology \u201d in5th International Conference on Artificial Intelligence and Computer Applications (ICAICA)(IEEE 2023) 1\u2013477 https:\/\/doi.org\/10.1109\/ICAICA58456.2023.10405405.","DOI":"10.1109\/ICAICA58456.2023.10405405"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.70182"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40799\u2010022\u201000577\u20102"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr8111464"},{"key":"e_1_2_11_23_1","unstructured":"B.AksoyandK.Ozsoy \u201cDeep Learning\u2010Based Classification of 3D Printing Defects \u201d inInternational Scientific Research and Innovation Congress(Venedik 2024) 209\u2013220."},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"M.Cao L.Fu K.Zhou andF.Ai \u201cImproved 3d Printing Extrusion Defect Detection Method Based on Yolo\u2010V8 \u201d preprint SSRN April 18 2024 https:\/\/ssrn.com\/abstract=4800007.","DOI":"10.2139\/ssrn.4800007"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170\u2010024\u201014452\u20104"},{"issue":"28","key":"e_1_2_11_26_1","first-page":"1","article-title":"A Real\u2010Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies","volume":"15","author":"Wang W.","year":"2024","journal-title":"Micromachines"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126863"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1089\/3dp.2021.0231"},{"key":"e_1_2_11_29_1","unstructured":"\u201cBlender Free and Open Source 3D Creation Suite \u201d Blender published2024 https:\/\/www.blender.org\/."},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.888718"},{"key":"e_1_2_11_31_1","unstructured":"\u201cDetection of ArUco Boards \u201d accessed January 5 2026 https:\/\/docs.opencv.org\/4.x\/d5\/dae\/tutorial_aruco_detection.html."},{"key":"e_1_2_11_32_1","doi-asserted-by":"crossref","unstructured":"R.Zhang P.Isola A. A.Efros E.Shechtman andO.Wang \u201cThe Unreasonable Effectiveness of Deep Features as a Perceptual Metric \u201d inIEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2018) 586\u2013595 https:\/\/doi.org\/10.1109\/CVPR.2018.00068.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"K.Roth L.Pemula J.Zepeda B.Scholkopf T.Brox andP.Gehler \u201cTowards Total Recall in Industrial Anomaly Detection \u201d inIEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2022) 14318\u201314328 https:\/\/doi.org\/10.1109\/CVPR52688.2022.01392.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_2_11_34_1","doi-asserted-by":"crossref","unstructured":"G.OhandJ.Shin \u201cPatch Core++: Augmenting Coreset for Superior Industrial Anomaly Detection \u201d inIEEE International Conference on Consumer Electronics\u2010Asia(IEEE 2024) 222\u2013227 https:\/\/doi.org\/10.1109\/ICCE\u2010Asia63397.2024.10773978.","DOI":"10.1109\/ICCE-Asia63397.2024.10773978"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3465446"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"K.He X.Zhang S.Ren andJ.Sun \u201cDeep Residual Learning for Image Recognition \u201d inIEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2016) 770\u2013778 https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"T.Aota L. T. T.Tong andT.Okatani \u201cZero\u2010Shot Versus Many\u2010Shot: Unsupervised Texture Anomaly Detection \u201d inIEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)(Wikoloa 2023) 5564\u20135572 https:\/\/doi.org\/10.1109\/WACV56688.2023.00552.","DOI":"10.1109\/WACV56688.2023.00552"},{"key":"e_1_2_11_38_1","doi-asserted-by":"crossref","unstructured":"T.Defard A.Setkov A.Loesch andR.Audigier \u201cPaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization \u201d inPattern Recognition. ICPR International Workshops and Challenges(Springer International Publishing 2021) 475\u2013489.","DOI":"10.1007\/978-3-030-68799-1_35"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70281","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70281","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:09:27Z","timestamp":1773043767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70281"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70281"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70281","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-11-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-31","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70281"}}