Preprint
A multi-scale a contrario method for unsupervised image anomaly detection
Fecha
2021Registro en:
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
Autor
Tailanian, Matias
Musé, Pablo
Pardo, Álvaro
Institución
Resumen
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.