A graph model-based multiscale feature fitting method for unsupervised anomaly detection

doi:10.1016/j.patcog.2023.109373

A graph model-based multiscale feature fitting method for unsupervised anomaly detection

2023-06-01

6

PRE

AI

DOI：10.1016/j.patcog.2023.109373

Original

Original request for help

Save

Abstract

En 中文

Anomaly detection and localization without prior knowledge is a challenging problem in industrial manu-facturing due to the complexity and variety of anomaly types. Most of the existing methods have achieved considerable anomaly detection performance based on the distance between normal features and abnor-mal features. However, when the defect area is hard to distinguish from the background or the defect area is small, the distance between normal and abnormal features will be too close to detect anomaly areas. In addition, existing methods do not consider the influences of features in different layers with differ-ent anomaly sizes. In this paper, a graph model-based multiscale feature fitting method is proposed for unsupervised anomaly detection. Specifically, we build a graph model based on the K nearest neighbors of an anchor image. The feature fitting and anomaly scores of the anchor images in the graph vertices are calculated next. Finally, a weighted multiscale anomaly map matching method is proposed to detect and locate the anomaly regions of test images. Compared with the state-of-the-art methods, our pro-posed method achieves competitive improvement in anomaly detection and localization on the MVTec AD dataset, the two KolektorSDD datasets, and the mSTC dataset.(c) 2023 Elsevier Ltd. All rights reserved.

Keywords:

Anomaly detection

Unsupervised learning

Graph model

Feature fitting representation

A graph model-based multiscale feature fitting method for unsupervised anomaly detection

Abstract

Journal

Organization