{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:11:08Z","timestamp":1771679468494,"version":"3.50.1"},"reference-count":51,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T00:00:00Z","timestamp":1693612800000},"content-version":"vor","delay-in-days":244,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bonfiglioli Engineering"},{"name":"POR FSE"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Anomaly detection is nowadays increasingly used in industrial applications and processes. One of the main fields of the appliance is the visual inspection for surface anomaly detection, which aims to spot regions that deviate from regularity and consequently identify abnormal products. Defect localization is a key task that is usually achieved using a basic comparison between generated image and the original one, implementing some blob analysis or image\u2010editing algorithms in the postprocessing step, which is very biased towards the source dataset, and they are unable to generalize. Furthermore, in industrial applications, the totality of the image is not always interesting but could be one or some regions of interest (ROIs), where only in those areas there are relevant anomalies to be spotted. For these reasons, we propose a new architecture composed by two blocks. The first block is a generative adversarial network (GAN), based on a residual autoencoder (ResAE), to perform reconstruction and denoising processes, while the second block produces image segmentation, spotting defects. This method learns from a dataset composed of good products and generated synthetic defects. The discriminative network is trained using a ROI for each image contained in the training dataset. The network will learn in which area anomalies are relevant. This approach guarantees the reduction of using preprocessing algorithms, formerly developed with blob analysis and image\u2010editing procedures. To test our model, we used challenging MVTec anomaly detection datasets and an industrial large dataset of pharmaceutical BFS strips of vials. This set constitutes a more realistic use case of the aforementioned network.<\/jats:p>","DOI":"10.1155\/2023\/7773481","type":"journal-article","created":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T19:50:06Z","timestamp":1693684206000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["GRD\u2010Net: Generative\u2010Reconstructive\u2010Discriminative Anomaly Detection with Region of Interest Attention Module"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2578-3211","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Ferrari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7656-7204","authenticated-orcid":false,"given":"Michele","family":"Fraccaroli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2747-4292","authenticated-orcid":false,"given":"Evelina","family":"Lamma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,9,2]]},"reference":[{"key":"e_1_2_10_1_2","unstructured":"BankD. KoenigsteinN. andGiryesR. Autoencoders 2020 https:\/\/arxiv.org\/abs\/2003.05991."},{"key":"e_1_2_10_2_2","unstructured":"MichelucciU. An introduction to autoencoders 2022 https:\/\/arxiv.org\/abs\/2201.03898."},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"KingmaD. P.andWellingM. An introduction to variational autoencoders 2019 https:\/\/arxiv.org\/abs\/1906.02691.","DOI":"10.1561\/9781680836233"},{"key":"e_1_2_10_4_2","unstructured":"KingmaD. P.andWellingM. Auto-encoding variational bayes 2013 https:\/\/arxiv.org\/abs\/1312.6114."},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"ZavrtanikV. KristanM. andSko\u010dajD. Draem-a discriminatively trained reconstruction embedding for surface anomaly detection Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2021 Montreal BC Canada 8330\u20138339.","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"e_1_2_10_7_2","first-page":"622","volume-title":"Asian Conference on Computer Vision","author":"Akcay S.","year":"2018"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3064819"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"Ak\u00e7ayS. Atapour-AbarghoueiA. andBreckonT. P. Skip-ganomaly: skip connected and adversarially trained encoder-decoder anomaly detection Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN) July 2019 Budapest Hungary IEEE 1\u20138.","DOI":"10.1109\/IJCNN.2019.8851808"},{"key":"e_1_2_10_10_2","unstructured":"PaulB. L\u00f6weS. FauserM. SattleggerD. andStegerC. Improving unsupervised defect segmentation by applying structural similarity to autoencoders 2018 https:\/\/arxiv.org\/abs\/1807.02011."},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"GongD. LiuL. LeV. SahaB. MansourM. R. VenkateshS. andAnton van denH. Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection Proceedings of the IEEE\/CVF International Conference on Computer Vision June 2019 Montreal BC Canada 1705\u20131714.","DOI":"10.1109\/ICCV.2019.00179"},{"key":"e_1_2_10_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_29"},{"key":"e_1_2_10_13_2","article-title":"Generative probabilistic novelty detection with adversarial autoencoders","volume":"31","author":"Pidhorskyi S.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"SabokrouM. KhalooeiM. FathyM. andAdeliE. Adversarially learned one-class classifier for novelty detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Vancouver BC Canada 3379\u20133388.","DOI":"10.1109\/CVPR.2018.00356"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.093"},{"key":"e_1_2_10_16_2","unstructured":"PaulB. FauserM. SattleggerD. andStegerC. Mvtec ad\u2013a comprehensive real-world dataset for unsupervised anomaly detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 9592\u20139600."},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22974"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"PereraP. RameshN. andXiangB. Ocgan: one-class novelty detection using gans with constrained latent representations Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2019 Baltimore MD USA 2898\u20132906.","DOI":"10.1109\/CVPR.2019.00301"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"RippelO. MertensP. andMerhofD. Modeling the distribution of normal data in pre-trained deep features for anomaly detection Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR) January 2021 Milan Italy IEEE 6726\u20136733.","DOI":"10.1109\/ICPR48806.2021.9412109"},{"key":"e_1_2_10_20_2","unstructured":"BergmanL. CohenN. andHoshenY. Deep nearest neighbor anomaly detection 2020 https:\/\/arxiv.org\/abs\/2002.10445."},{"key":"e_1_2_10_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/s18010209"},{"key":"e_1_2_10_22_2","unstructured":"CohenN.andHoshenY. Sub-image anomaly detection with deep pyramid correspondences 2020 https:\/\/arxiv.org\/abs\/2005.02357."},{"key":"e_1_2_10_23_2","doi-asserted-by":"crossref","unstructured":"DefardT. SetkovA. LoeschA. andAudigierR. Padim: a patch distribution modeling framework for anomaly detection and localization Proceedings of the International Conference on Pattern Recognition March 2021 Berlin Germany Springer 475\u2013489.","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"RothK. PemulaL. ZepedaJ. Sch\u00f6lkopfB. BroxT. andGehlerP. Towards total recall in industrial anomaly detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2022 New Orleans LA USA 14318\u201314328.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"e_1_2_10_25_2","unstructured":"DinhL. Sohl-DicksteinJ. andBengioS. Density estimation using real nvp 2016 https:\/\/arxiv.org\/abs\/1605.08803."},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.018"},{"key":"e_1_2_10_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"e_1_2_10_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"e_1_2_10_29_2","doi-asserted-by":"crossref","unstructured":"RudolphM. WandtB. andRosenhahnB. Same same but differnet: semi-supervised defect detection with normalizing flows Proceedings of the IEEE\/CVF winter conference on applications of computer vision Augest 2021 Hanover Germany 1907\u20131916.","DOI":"10.1109\/WACV48630.2021.00195"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"GudovskiyD. IshizakaS. andKozukaK. Cflow-ad: real-time unsupervised anomaly detection with localization via conditional normalizing flows Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision July 2022 Tokyo Japan 98\u2013107.","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"BaeJ. LeeJ.-H. andKimS. Pni: industrial anomaly detection using position and neighborhood information 2023 https:\/\/arxiv.org\/abs\/2211.12634.","DOI":"10.1109\/ICCV51070.2023.00586"},{"key":"e_1_2_10_32_2","unstructured":"PaulB. FauserM. SattleggerD. andStegerC. Uninformed students: student-teacher anomaly detection with discriminative latent embeddings 2019 https:\/\/arxiv.org\/abs\/1911.02357."},{"key":"e_1_2_10_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01578-9"},{"key":"e_1_2_10_34_2","doi-asserted-by":"crossref","unstructured":"BatznerK. HecklerL. andK\u00f6nigR. Efficientad: accurate visual anomaly detection at millisecond-level latencies 2023 https:\/\/arxiv.org\/abs\/2303.14535.","DOI":"10.1109\/WACV57701.2024.00020"},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"LiD. ChenD. ShiL. JinB. GohJ. andNgS.-K. Mad-gan: multivariate anomaly detection for time series data with generative adversarial networks 2019 https:\/\/arxiv.org\/abs\/1901.04997.","DOI":"10.1007\/978-3-030-30490-4_56"},{"key":"e_1_2_10_36_2","doi-asserted-by":"crossref","unstructured":"ZhuG. ZhaoH. LiuH. andSunH. A novel lstm-gan algorithm for time series anomaly detection 2019 Prognostics and System Health Management Conference (PHM-Qingdao) October 2019 Qingdao China 1\u20136.","DOI":"10.1109\/PHM-Qingdao46334.2019.8942842"},{"key":"e_1_2_10_37_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20133738"},{"key":"e_1_2_10_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2944689"},{"key":"e_1_2_10_39_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20185305"},{"key":"e_1_2_10_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2021.3078381"},{"key":"e_1_2_10_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107969"},{"key":"e_1_2_10_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/325165.325247"},{"key":"e_1_2_10_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"e_1_2_10_44_2","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"e_1_2_10_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765202"},{"key":"e_1_2_10_46_2","unstructured":"MakhzaniA. ShlensJ. JaitlyN. GoodfellowI. andFreyB. Adversarial autoencoders 2015 https:\/\/arxiv.org\/abs\/1511.05644."},{"key":"e_1_2_10_47_2","unstructured":"MirzaM.andSimonO. Conditional generative adversarial nets 2014 https:\/\/arxiv.org\/abs\/1411.1784."},{"key":"e_1_2_10_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"e_1_2_10_49_2","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition 2015 https:\/\/arxiv.org\/abs\/1512.03385."},{"key":"e_1_2_10_50_2","article-title":"Exploiting cnn\u2019s visual explanations to drive anomaly detection","author":"Fraccaroli M.","year":"2021","journal-title":"Submitted to Applied Intelligence"},{"key":"e_1_2_10_51_2","unstructured":"FraccaroliM. BizzarriA. CasellatiP. andLammaE. Cross entropy overlap distance 2022 https:\/\/ml.unife.it\/wp-content\/uploads\/Papers\/FraBizCasLam-ITAL_IA22.pdf."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/7773481.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/7773481.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/7773481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:29:10Z","timestamp":1735622950000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/7773481"}},"subtitle":[],"editor":[{"given":"Mohammad R.","family":"Khosravi","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/7773481"],"URL":"https:\/\/doi.org\/10.1155\/2023\/7773481","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-12-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7773481"}}