dc.contributor | Tailanian Matias, Universidad de la República (Uruguay). Facultad de Ingeniería. | |
dc.contributor | Musé Pablo, Universidad de la República (Uruguay). Facultad de Ingeniería. | |
dc.contributor | Pardo Álvaro, Universidad Católica del Uruguay | |
dc.creator | Tailanian, Matias | |
dc.creator | Musé, Pablo | |
dc.creator | Pardo, Álvaro | |
dc.date.accessioned | 2022-05-19T12:02:04Z | |
dc.date.accessioned | 2022-10-28T20:22:20Z | |
dc.date.available | 2022-05-19T12:02:04Z | |
dc.date.available | 2022-10-28T20:22:20Z | |
dc.date.created | 2022-05-19T12:02:04Z | |
dc.date.issued | 2021 | |
dc.identifier | Tailanian, M., Musé, P. y Pardo, Á. A multi-scale a contrario method for unsupervised image anomaly detection. [Preprint] Publicado en : 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA, 13-16 dec. 2021, pp. 179-184. DOI 10.1109/ICMLA52953.2021.00035 | |
dc.identifier | https://ieeexplore.ieee.org/document/9680125 | |
dc.identifier | https://hdl.handle.net/20.500.12008/31622 | |
dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/4985505 | |
dc.description.abstract | Anomalies can be defined as any non-random structure which deviates from normality. Anomaly detection methods reported in the literature are numerous and diverse, as what is considered anomalous usually varies depending on particular scenarios and applications. In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions. We evaluate filters learned from the image under analysis via patch PCA and the feature maps obtained from a pre-trained deep neural network (Resnet). The proposed method is multi-scale and fully unsupervised, and is able to detect anomalies in a wide variety of scenarios. While the end goal of this work is the detection of subtle defects in leather samples for the automotive industry, we show that the same algorithm achieves state-of-the-art results in public anomalies datasets. | |
dc.language | en | |
dc.publisher | IEEE | |
dc.relation | 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA, 13-16 dec. 2021, pp. 179-184. | |
dc.rights | Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) | |
dc.rights | Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014) | |
dc.subject | Industries | |
dc.subject | Deep learning | |
dc.subject | Conferences | |
dc.subject | Neural networks | |
dc.subject | Feature extraction | |
dc.subject | Task analysis | |
dc.subject | Anomaly detection | |
dc.subject | A contrario detection | |
dc.subject | Number of false alarms | |
dc.subject | NFA | |
dc.subject | Mahalanobis distance | |
dc.subject | Principal components analysis | |
dc.subject | PCA | |
dc.subject | Multi-scale | |
dc.title | A multi-scale a contrario method for unsupervised image anomaly detection | |
dc.type | Preprint | |