{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:19:25Z","timestamp":1784783965744,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T00:00:00Z","timestamp":1628208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003185","name":"Fraunhofer-Gesellschaft","doi-asserted-by":"publisher","award":["WISA 833 959"],"award-info":[{"award-number":["WISA 833 959"]}],"id":[{"id":"10.13039\/501100003185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Anomaly detection is a critical problem in the manufacturing industry. In many applications, images of objects to be analyzed are captured from multiple perspectives which can be exploited to improve the robustness of anomaly detection. In this work, we build upon the deep support vector data description algorithm and address multi-perspective anomaly detection using three different fusion techniques, i.e., early fusion, late fusion, and late fusion with multiple decoders. We employ different augmentation techniques with a denoising process to deal with scarce one-class data, which further improves the performance (ROC AUC =80%). Furthermore, we introduce the dices dataset, which consists of over 2000 grayscale images of falling dices from multiple perspectives, with 5% of the images containing rare anomalies (e.g., drill holes, sawing, or scratches). We evaluate our approach on the new dices dataset using images from two different perspectives and also benchmark on the standard MNIST dataset. Extensive experiments demonstrate that our proposed multi-perspective approach exceeds the state-of-the-art single-perspective anomaly detection on both the MNIST and dices datasets. To the best of our knowledge, this is the first work that focuses on addressing multi-perspective anomaly detection in images by jointly using different perspectives together with one single objective function for anomaly detection.<\/jats:p>","DOI":"10.3390\/s21165311","type":"journal-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T05:22:01Z","timestamp":1628227321000},"page":"5311","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Multi-Perspective Anomaly Detection"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5304-6294","authenticated-orcid":false,"given":"Peter","family":"Jakob","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manav","family":"Madan","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-9283","authenticated-orcid":false,"given":"Tobias","family":"Schmid-Schirling","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4710-3114","authenticated-orcid":false,"given":"Abhinav","family":"Valada","sequence":"additional","affiliation":[{"name":"Robot Learning Lab., University of Freiburg, 79110 Freiburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Liu, L., and \u00d6zsu, M.T. (2017). Outlier Detection. Encyclopedia of Database Systems, Springer.","DOI":"10.1007\/978-1-4899-7993-3"},{"key":"ref_2","unstructured":"Minhas, M.S., and Zelek, J. (2019). Anomaly Detection in Images. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1017\/S026988891300043X","article-title":"One-class classification: Taxonomy of study and review of techniques","volume":"29","author":"Khan","year":"2014","journal-title":"Knowl. Eng. Rev."},{"key":"ref_4","unstructured":"Sch\u00f6lkopf, B., Williamson, R.C., Smola, A.J., Shawe-Taylor, J., and Platt, J.C. (2000). Support vector method for novelty detection. Advances in Neural Information Processing Systems, MIT Pres."},{"key":"ref_5","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_6","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 35th International Conference on Machine Learning, Stockholm Sweden."},{"key":"ref_7","unstructured":"Chalapathy, R., Menon, A.K., and Chawla, S. (2018). Anomaly detection using one-class neural networks. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/B:MACH.0000008084.60811.49","article-title":"Support vector data description","volume":"54","author":"Tax","year":"2004","journal-title":"Mach. Learn."},{"key":"ref_9","unstructured":"LeCun, Y., Cortes, C., and MNIST (2020, June 15). Handwritten Digit Database. Available online: http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1109\/JPROC.2021.3052449","article-title":"A Unifying Review of Deep and Shallow Anomaly Detection","volume":"109","author":"Ruff","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_11","unstructured":"Seeb\u00f6ck, P., Waldstein, S., Klimscha, S., Gerendas, B.S., Donner, R., Schlegl, T., Schmidt-Erfurth, U., and Langs, G. (2016). Identifying and Categorizing Anomalies in Retinal Imaging Data. arXiv."},{"key":"ref_12","unstructured":"Kayser, M., and Zhong, V. (2015). Denoising Convolutional Autoencoders for Noisy Speech Recognition, Stanford University. CS231 Standford Reports."},{"key":"ref_13","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_14","unstructured":"Ruff, L., Vandermeulen, R.A., G\u00f6rnitz, N., Binder, A., M\u00fcller, E., M\u00fcller, K.R., and Kloft, M. (2020). Deep Semi-Supervised Anomaly Detection. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ji, Y., Huang, L., He, H., Wang, C., Xie, G., Shi, W., and Lin, K. (2019, January 8\u201311). Multi-view Outlier Detection in Deep Intact Space. Proceedings of the 2019 IEEE International Conference on Data Mining (ICDM), Beijing, China.","DOI":"10.1109\/ICDM.2019.00136"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","article-title":"Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope","volume":"42","author":"Oliva","year":"2001","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","first-page":"1","article-title":"Fast Multi-View Outlier Detection via Deep Encoder","volume":"1","author":"Hou","year":"2020","journal-title":"IEEE Trans. Big Data"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015). Multi-view Convolutional Neural Networks for 3D Shape Recognition. arXiv.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Choy, C.B., Xu, D., Gwak, J., Chen, K., and Savarese, S. (2016). 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction. arXiv.","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.patcog.2018.05.004","article-title":"Contactless and partial 3D fingerprint recognition using multi-view deep representation","volume":"83","author":"Lin","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_21","unstructured":"Zhu, P., Hui, B., Zhang, C., Du, D., Wen, L., and Hu, Q. (2019). Multi-view Deep Subspace Clustering Networks. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Seeland, M., and M\u00e4der, P. (2021). Multi-view classification with convolutional neural networks. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0245230"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.13031\/2013.29121","article-title":"Sensor fusion using fuzzy logic enhanced kalman filter for autonomous vehicle guidance in citrus groves","volume":"52","author":"Subramanian","year":"2009","journal-title":"Trans. ASABE"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kim, J., Koh, J., Kim, Y., Choi, J., Hwang, Y., and Choi, J.W. (2018). Robust Deep Multi-modal Learning Based on Gated Information Fusion Network. arXiv.","DOI":"10.1109\/IVS.2018.8500711"},{"key":"ref_25","unstructured":"Valada, A., Dhall, A., and Burgard, W. (2016, January 9\u201314). Convoluted mixture of deep experts for robust semantic segmentation. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop, State Estimation and Terrain Perception for All Terrain Mobile Robots, Daejeon, Korea."},{"key":"ref_26","unstructured":"Valada, A., Oliveira, G., Brox, T., and Burgard, W. (2016, January 18). Towards robust semantic segmentation using deep fusion. Proceedings of the Robotics: Science and Systems (RSS 2016) Workshop, Are the Sceptics Right? Limits and Potentials of Deep Learning in Robotics, Ann Arbor, MI, USA."},{"key":"ref_27","first-page":"9240407","article-title":"Multi-Input Convolutional Neural Network for Flower Grading","volume":"2017","author":"Sun","year":"2017","journal-title":"J. Electr. Comput. Eng."},{"key":"ref_28","first-page":"4894","article-title":"Multi-View Anomaly Detection: Neighborhood in Locality Matters","volume":"33","author":"Sheng","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_29","unstructured":"Yan, W.-J., Wu, Q., Liu, Y.-J., Wang, S.-J., and Fu, X. (2013, January 22\u201326). CASME database: A dataset of spontaneous micro-expressions collected from neutralized faces. Proceedings of the 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), Shanghai, China."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008, January 15\u201319). Isolation Forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_31","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"747","DOI":"10.21105\/joss.00747","article-title":"NN-SVG: Publication-Ready Neural Network Architecture Schematics","volume":"4","author":"LeNail","year":"2019","journal-title":"J. Open Source Softw."},{"key":"ref_33","unstructured":"Falkner, S., Klein, A., and Hutter, F. (2018). BOHB: Robust and efficient hyperparameter optimization at scale. arXiv."},{"key":"ref_34","unstructured":"Jakob, P., Basler, C., Schmid-Schirling, T., Brandenburg, A., and Carl, D. (2019). Schnelle Sortierung und Pr\u00fcfung von Sch\u00fcttgut im freien Fall am Beispiel Ventilfedern. Ilmenauer Federntag 2019: Neueste Erkenntnisse zu Funktion, Berechnung, Pr\u00fcfung und Gestaltung von Federn und Werkstoffen, Isle Steuerungstechnik und Leistungselektronik."},{"key":"ref_35","unstructured":"Madan, M., and Jakob, P. (2021). Two-Perspective Dices Dataset for Anomaly Detection. arXiv."},{"key":"ref_36","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5311\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:41:28Z","timestamp":1760164888000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,6]]},"references-count":36,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21165311"],"URL":"https:\/\/doi.org\/10.3390\/s21165311","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,6]]}}}