Unsupervised Anomaly Detection and Segmentation on Dirty Datasets

Jiahao Guo, Xiaohuo Yu and Lu Wang
Additional contact information
Jiahao Guo: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Xiaohuo Yu: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Lu Wang: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

Future Internet, 2022, vol. 14, issue 3, 1-17

Abstract: Industrial quality control is an important task. Most of the existing vision-based unsupervised industrial anomaly detection and segmentation methods require that the training set only consists of normal samples, which is difficult to ensure in practice. This paper proposes an unsupervised framework to solve the industrial anomaly detection and segmentation problem when the training set contains anomaly samples. Our framework uses a model pretrained on ImageNet as a feature extractor to extract patch-level features. After that, we propose a trimming method to estimate a robust Gaussian distribution based on the patch features at each position. Then, with an iterative filtering process, we can iteratively filter out the anomaly samples in the training set and re-estimate the Gaussian distribution at each position. In the prediction phase, the Mahalanobis distance between a patch feature vector and the center of the Gaussian distribution at the corresponding position is used as the anomaly score of this patch. The subsequent anomaly region segmentation is performed based on the patch anomaly score. We tested the proposed method on three datasets containing the anomaly samples and obtained state-of-the-art performance.

Keywords: anomaly detection and segmentation; unsupervised method; noise resistance (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/3/86/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/3/86/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:3:p:86-:d:770077

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().