Ultrasound Anomaly Detection Based on Variational Autoencoders

Analysis of ultrasonic testing (UT) data is a time-consuming assignment. In order to make it less demanding we propose an approach based on a variational autoencoder (VAE) to filter out the scans without anomalies/defects and in doing so, partially automate the procedure. The implemented approach us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) S. 225 - 229
Hauptverfasser: Milkovic, Fran, Filipovic, Branimir, Subasic, Marko, Petkovic, Tomislav, Loncaric, Sven, Budimir, Marko
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 13.09.2021
Schlagworte:
Acoustics
Anomaly detection
computer vision
deep learning
Image coding
Image reconstruction
Signal processing
Testing
Ultrasonic imaging
ultrasonic testing
variational autoencoder
ISSN:1849-2266
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Analysis of ultrasonic testing (UT) data is a time-consuming assignment. In order to make it less demanding we propose an approach based on a variational autoencoder (VAE) to filter out the scans without anomalies/defects and in doing so, partially automate the procedure. The implemented approach uses an additional encoder network allowing to encode the reconstructed images. The differences in encodings of input and reconstructed images have shown to be good indicators of anomalous data. Anomaly detection results surpass the results of other VAE based anomaly criteria.
ISSN:1849-2266
DOI:10.1109/ISPA52656.2021.9552041