A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection

Matias Tailanian, Pablo Muse, Alvaro Pardo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 20th IEEE International Conference on Machine Learning and Applications, ICMLA 2021
EditorsM. Arif Wani, Ishwar K. Sethi, Weisong Shi, Guangzhi Qu, Daniela Stan Raicu, Ruoming Jin
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages179-184
Number of pages6
ISBN (Electronic)9781665443371
DOIs
StatePublished - 2021
Event20th IEEE International Conference on Machine Learning and Applications, ICMLA 2021 - Virtual, Online, United States
Duration: 13 Dec 202116 Dec 2021

Publication series

NameProceedings - 20th IEEE International Conference on Machine Learning and Applications, ICMLA 2021

Conference

Conference20th IEEE International Conference on Machine Learning and Applications, ICMLA 2021
Country/TerritoryUnited States
CityVirtual, Online
Period13/12/2116/12/21

Keywords

  • A contrario detection
  • Anomaly detection
  • Mahalanobis distance
  • Multi-scale
  • NFA
  • Number of false alarms
  • PCA
  • Principal components analysis

Fingerprint

Dive into the research topics of 'A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection'. Together they form a unique fingerprint.

Cite this