{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:29:34Z","timestamp":1775838574134,"version":"3.50.1"},"reference-count":60,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:00:00Z","timestamp":1673740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science and Technology, Taiwan","award":["MOST 110-2221-E-155-039-MY3"],"award-info":[{"award-number":["MOST 110-2221-E-155-039-MY3"]}]},{"name":"Ministry of Science and Technology, Taiwan","award":["MOST 111-2221-E-155-039-MY3"],"award-info":[{"award-number":["MOST 111-2221-E-155-039-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Anomalies are a set of samples that do not follow the normal behavior of the majority of data. In an industrial dataset, anomalies appear in a very small number of samples. Currently, deep learning-based models have achieved important advances in image anomaly detection. However, with general models, real-world application data consisting of non-ideal images, also known as poison images, become a challenge. When the work environment is not conducive to consistently acquiring a good or ideal sample, an additional adaptive learning model is needed. In this work, we design a potential methodology to tackle poison or non-ideal images that commonly appear in industrial production lines by enhancing the existing training data. We propose Hierarchical Image Transformation and Multi-level Features (HIT-MiLF) modules for an anomaly detection network to adapt to perturbances from novelties in testing images. This approach provides a hierarchical process for image transformation during pre-processing and explores the most efficient layer of extracted features from a CNN backbone. The model generates new transformations of training samples that simulate the non-ideal condition and learn the normality in high-dimensional features before applying a Gaussian mixture model to detect the anomalies from new data that it has never seen before. Our experimental results show that hierarchical transformation and multi-level feature exploration improve the baseline performance on industrial metal datasets.<\/jats:p>","DOI":"10.3390\/s23020988","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T05:30:07Z","timestamp":1673847007000},"page":"988","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Hierarchical Image Transformation and Multi-Level Features for Anomaly Defect Detection"],"prefix":"10.3390","volume":"23","author":[{"given":"Isack","family":"Farady","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Mercu Buana University, Jakarta 11650, Indonesia"},{"name":"Department of Electrical and Communication Engineering, Yuan Ze University, Taoyuan 320, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Chen","family":"Kuo","sequence":"additional","affiliation":[{"name":"National Center for High-Performance Computing, National Applied Research Laboratories, Hsinchu 300, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4394-2770","authenticated-orcid":false,"given":"Hui-Fuang","family":"Ng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University Tunku Abdul Rahman, Kampar 31900, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0401-8473","authenticated-orcid":false,"given":"Chih-Yang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Communication Engineering, Yuan Ze University, Taoyuan 320, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1541880.1541882","article-title":"Anomaly detection: A survey","volume":"41","author":"Chandola","year":"2009","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_2","unstructured":"Szegedy, C., Toshev, A., and Erhan, D. (2013, January 5\u201310). Deep neural networks for object detection. Advances in neural information processing systems 26. Proceedings of the 27th Annual Conference on Neural Information Processing Systems 2013, Lake Tahoe, NV, USA."},{"key":"ref_3","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Saleh, B., Farhadi, A., and Elgammal, A. (2013, January 23\u201328). Object-centric anomaly detection by attribute-based reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.107"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Napoletano, P., Piccoli, F., and Schettini, R. (2018). Anomaly detection in nanofibrous materials by CNN-based self-similarity. Sensors, 18.","DOI":"10.3390\/s18010209"},{"key":"ref_7","unstructured":"Cohen, N., and Hoshen, Y. (2020). Sub-image anomaly detection with deep pyramid correspondences. arXiv."},{"key":"ref_8","first-page":"38","article-title":"Deep learning for anomaly detection: A review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_9","unstructured":"Qiu, C., Pfrommer, T., Kloft, M., Mandt, S., and Rudolph, M. (2021, January 18\u201324). Neural transformation learning for deep anomaly detection beyond images. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_10","unstructured":"Minhas, M.S., and Zelek, J. (2019). Anomaly detection in images. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1007\/s10586-017-1117-8","article-title":"A survey of deep learning-based network anomaly detection","volume":"22","author":"Kwon","year":"2019","journal-title":"Clust. Comput."},{"key":"ref_12","unstructured":"Anderson, D., Frivold, T., and Valdes, A. (1995). Next-Generation Intrusion Detection Expert System (NIDES): A Summary, SRI International. Tech. Rep. SRI-CSL-97-07."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_14","unstructured":"Li, K.-L., Huang, H.-K., Tian, S.-F., and Xu, W. (2003, January 5). Improving one-class SVM for anomaly detection. Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No. 03EX693), Xi\u2019an, China."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1162\/089976601750264965","article-title":"Estimating the support of a high-dimensional distribution","volume":"13","author":"Platt","year":"2001","journal-title":"Neural Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann. Math. Stat."},{"key":"ref_17","unstructured":"Latecki, L.J., Lazarevic, A., and Pokrajac, D. (September, January 30). Outlier detection with kernel density functions. Proceedings of the International Workshop on Machine Learning and Data Mining in Pattern Recognition, New York, NY, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/TKDE.2018.2882404","article-title":"Anomaly detection using local kernel density estimation and context-based regression","volume":"32","author":"Hu","year":"2018","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.jnca.2016.04.007","article-title":"Fraud detection system: A survey","volume":"68","author":"Abdallah","year":"2016","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"19161","DOI":"10.1109\/ACCESS.2018.2816564","article-title":"CoDetect: Financial fraud detection with anomaly feature detection","volume":"6","author":"Huang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113303","DOI":"10.1016\/j.dss.2020.113303","article-title":"Fraud detection: A systematic literature review of graph-based anomaly detection approaches","volume":"133","author":"Pourhabibi","year":"2020","journal-title":"Decis. Support Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Diro, A., Chilamkurti, N., Nguyen, V.-D., and Heyne, W. (2021). A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms. Sensors, 21.","DOI":"10.3390\/s21248320"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.jnca.2015.11.016","article-title":"A survey of network anomaly detection techniques","volume":"60","author":"Ahmed","year":"2016","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1109\/TKDE.2010.235","article-title":"Anomaly detection for discrete sequences: A survey","volume":"24","author":"Chandola","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3464423","article-title":"Deep learning for medical anomaly detection\u2013a survey","volume":"54","author":"Fernando","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1109\/TBCAS.2013.2245664","article-title":"MedMon: Securing medical devices through wireless monitoring and anomaly detection","volume":"7","author":"Zhang","year":"2013","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wei, Q., Ren, Y., Hou, R., Shi, B., Lo, J.Y., and Carin, L. (2018, January 12\u201315). Anomaly detection for medical images based on a one-class classification. Proceedings of the Medical Imaging 2018: Computer-Aided Diagnosis, Houston, TX, USA.","DOI":"10.1117\/12.2293408"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yeo, C.K., Lee, B.S., and Lau, C.T. (2018, January 17\u201320). Autoencoder-based network anomaly detection. Proceedings of the 2018 Wireless Telecommunications Symposium (WTS), Phoenix, AZ, USA.","DOI":"10.1109\/WTS.2018.8363930"},{"key":"ref_29","unstructured":"Gong, D., Liu, L., Le, V., Saha, B., Mansour, M.R., Venkatesh, S., and Hengel, A.v.d. (November, January 27). Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_30","first-page":"1672","article-title":"In-network PCA and anomaly detection","volume":"19","author":"Huang","year":"2006","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"118571","DOI":"10.1109\/ACCESS.2021.3107163","article-title":"Anomaly detection in medical imaging with deep perceptual autoencoders","volume":"9","author":"Shvetsova","year":"2021","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Lawson, W., Bekele, E., and Sullivan, K. (2017, January 21\u201326). Finding anomalies with generative adversarial networks for a patrolbot. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.68"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Schlegl, T., Seeb\u00f6ck, P., Waldstein, S.M., Schmidt-Erfurth, U., and Langs, G. (2017, January 25\u201330). Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. Proceedings of the International Conference on Information Processing in Medical Imaging, Boone, NC, USA.","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks","volume":"54","author":"Schlegl","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_35","unstructured":"Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., and Lakshminarayanan, B. (2018). Do deep generative models know what they don\u2019t know?. arXiv."},{"key":"ref_36","unstructured":"Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., M\u00fcller, E., and Kloft, M. (2018, January 10\u201315). Deep one-class classification. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Perera, P., Nallapati, R., and Xiang, B. (2019, January 15\u201320). Ocgan: One-class novelty detection using gans with constrained latent representations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00301"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5450","DOI":"10.1109\/TIP.2019.2917862","article-title":"Learning deep features for one-class classification","volume":"28","author":"Perera","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1007\/s10618-014-0365-y","article-title":"Graph based anomaly detection and description: A survey","volume":"29","author":"Akoglu","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3469","DOI":"10.1109\/TII.2020.3022432","article-title":"Variational LSTM enhanced anomaly detection for industrial big data","volume":"17","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Yi, J., and Yoon, S. (2020\u20134, January 30). Patch svdd: Patch-level svdd for anomaly detection and segmentation. Proceedings of the Asian Conference on Computer Vision, Kyoto, Japan.","DOI":"10.1007\/978-3-030-69544-6_23"},{"key":"ref_42","first-page":"21038","article-title":"Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features","volume":"33","author":"Schirrmeister","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2019, January 15\u201320). MVTec AD--A comprehensive real-world dataset for unsupervised anomaly detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., and Summers, R.M. (2017, January 21\u201326). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Bejnordi","year":"2017","journal-title":"Jama"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2021, January 10\u201315). Padim: A patch distribution modeling framework for anomaly detection and localization. Proceedings of the International Conference on Pattern Recognition, Milan, Italy.","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref_48","unstructured":"Denouden, T., Salay, R., Czarnecki, K., Abdelzad, V., Phan, B., and Vernekar, S. (2018). Improving reconstruction autoencoder out-of-distribution detection with mahalanobis distance. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Rippel, O., Mertens, P., and Merhof, D. (2021, January 10\u201315). 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), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412109"},{"key":"ref_50","first-page":"937","article-title":"Learning a Mahalanobis metric from equivalence constraints","volume":"6","author":"Hertz","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0169-7439(99)00047-7","article-title":"The mahalanobis distance","volume":"50","author":"Massart","year":"2000","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_53","unstructured":"Zenati, H., Foo, C.S., Lecouat, B., Manek, G., and Chandrasekhar, V.R. (2018). Efficient gan-based anomaly detection. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Kim, J., Jeong, K., Choi, H., and Seo, K. (2020, January 23\u201328). GAN-based anomaly detection in imbalance problems. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-65414-6_11"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.neucom.2021.12.093","article-title":"GAN-based anomaly detection: A review","volume":"493","author":"Xia","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_56","first-page":"9758","article-title":"Deep anomaly detection using geometric transformations","volume":"31","author":"Golan","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Sheynin, S., Benaim, S., and Wolf, L. (2021, January 11\u201317). A hierarchical transformation-discriminating generative model for few shot anomaly detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00838"},{"key":"ref_58","unstructured":"(2021, November 11). Available online: https:\/\/www.kaggle.com\/datasets\/ravirajsinh45\/real-life-industrial-dataset-of-casting-product."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Akcay, S., Ameln, D., Vaidya, A., Lakshmanan, B., Ahuja, N., and Genc, U. (2022). Anomalib: A Deep Learning Library for Anomaly Detection. arXiv.","DOI":"10.1109\/ICIP46576.2022.9897283"},{"key":"ref_60","unstructured":"Ahuja, N.A., Ndiour, I., Kalyanpur, T., and Tickoo, O. (2019). Probabilistic modeling of deep features for out-of-distribution and adversarial detection. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/988\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:06:26Z","timestamp":1760119586000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/988"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,15]]},"references-count":60,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23020988"],"URL":"https:\/\/doi.org\/10.3390\/s23020988","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,15]]}}}