In this work, we investigate a methodology to per- form anomaly detection and localization in images. The method leverages both sparse representation learning and the adoption of a pre-trained neural network for classification purposes. The objective is to assess the effectiveness of the K-SVD sparse dictionary learning algorithm and understand the role of neural network activation maps as data descriptors. We extract meaningful representation features and build a sparse dictionary of the most expressive ones. The dictionary is built only over features coming from images without anomalies. Thus, images containing anomalies will either have a non-sparse representation as linear combinations of the dictionary elements or a high reconstruction error. We show that the proposed pipeline achieves state-of-the-art performance in terms of AUC-ROC score over benchmarks such as MVTec Anomaly Detection, Rd-MVTec Anomaly Detection, Magnetic Tiles Defect, BeanTech Anomaly Detection, Kolektor Surface Defect datasets.
Patchwise Sparse Dictionary Learning from pre-trained Neural Network Activation Maps for Anomaly Detection in Images
Stefano Samele;Matteo Matteucci
2022-01-01
Abstract
In this work, we investigate a methodology to per- form anomaly detection and localization in images. The method leverages both sparse representation learning and the adoption of a pre-trained neural network for classification purposes. The objective is to assess the effectiveness of the K-SVD sparse dictionary learning algorithm and understand the role of neural network activation maps as data descriptors. We extract meaningful representation features and build a sparse dictionary of the most expressive ones. The dictionary is built only over features coming from images without anomalies. Thus, images containing anomalies will either have a non-sparse representation as linear combinations of the dictionary elements or a high reconstruction error. We show that the proposed pipeline achieves state-of-the-art performance in terms of AUC-ROC score over benchmarks such as MVTec Anomaly Detection, Rd-MVTec Anomaly Detection, Magnetic Tiles Defect, BeanTech Anomaly Detection, Kolektor Surface Defect datasets.File | Dimensione | Formato | |
---|---|---|---|
PSDL_ICPR_2022_Camera_Ready.pdf
Accesso riservato
:
Publisher’s version
Dimensione
535.63 kB
Formato
Adobe PDF
|
535.63 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.