Tampere University of Technology

TUTCRIS Research Portal

Scale-invariant anomaly detection with multiscale group-sparse models

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

Details

Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
Pages3892-3896
Number of pages5
ISBN (Electronic)978-1-4673-9961-6
DOIs
Publication statusPublished - 19 Aug 2016
Publication typeA4 Article in a conference publication
EventIEEE International Conference on Image Processing -
Duration: 1 Jan 1900 → …

Publication series

Name
ISSN (Electronic)2381-8549

Conference

ConferenceIEEE International Conference on Image Processing
Period1/01/00 → …

Abstract

The automatic detection of anomalies, defined as patterns that are not encountered in representative set of normal images, is an important problem in industrial control and biomedical applications. We have shown that this problem can be successfully addressed by the sparse representation of individual image patches using a dictionary learned from a large set of patches extracted from normal images. Anomalous patches are detected as those for which the sparse representation on this dictionary exceeds sparsity or error tolerances. Unfortunately, this solution is not suitable for many real-world visual inspection-systems since it is not scale invariant: since the dictionary is learned at a single scale, patches in normal images acquired at a different magnification level might be detected as anomalous. We present an anomaly-detection algorithm that learns a dictionary that is invariant to a range of scale changes, and overcomes this limitation by use of an appropriate sparse coding stage. The algorithm was successfully tested in an industrial application by analyzing a dataset of Scanning Electron Microscope (SEM) images, which typically exhibit different magnification levels.

Keywords

  • Detectors, Dictionaries, Encoding, Monitoring, Production, Scanning electron microscopy, Training, Anomaly detection, dictionary learning, group sparsity, image analysis, sparse representations

Publication forum classification

Field of science, Statistics Finland

Downloads statistics

No data available