Image novelty detection based on mean-shift and typical set size
- The detection of anomalous or novel images given a training dataset of only clean reference data (inliers) is an important task in computer vision. We propose a new shallow approach that represents both inlier and outlier images as ensembles of patches, which allows us to effectively detect novelties as mean shifts between reference data and outliers with the Hotelling T2 test. Since mean-shift can only be detected when the outlier ensemble is sufficiently separate from the typical set of the inlier distribution, this typical set acts as a blind spot for novelty detection. We therefore minimize its estimated size as our selection rule for critical hyperparameters, such as, e.g., the size of the patches is crucial. To showcase the capabilities of our approach, we compare results with classical and deep learning methods on the popular datasets MNIST and CIFAR-10, and demonstrate its real-world applicability in a large-scale industrial inspection scenario.
Author: | Matthias Hermann, Bastian Goldlücke, Matthias O. FranzORCiDGND |
---|---|
DOI: | https://doi.org/10.1007/978-3-031-06430-2_63 |
ISBN: | 978-3-031-06429-6 |
ISBN: | 978-3-031-06430-2 |
Parent Title (English): | Image Analysis and Processing - ICIAP 2022, 21th International Conference, May 23 - 27 May 2022, Lecce, Italy, hybrid, Proceedings, Part I, (Lecture Notes in Computer Science, Volume 13231) |
Publisher: | Springer |
Place of publication: | Cham |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2022 |
Release Date: | 2022/12/07 |
Tag: | Image novelty detection; Independent component analysis; Mean-shift |
First Page: | 755 |
Last Page: | 766 |
Note: | Corresponding author: Matthias Hermann |
Relevance: | Peer reviewed nach anderen Listungen (mit Nachweis zum Peer Review Verfahren) |
Open Access?: | Nein |
Licence (German): | Urheberrechtlich geschützt |