Ultrasound Anomaly Detection Based on Variational Autoencoders (CROSBI ID 710709)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Milković, Fran ; Filipović, Branimir ; Subašić, Marko ; Petković, Tomislav ; Lončarić, Sven ; Budimir, Marko
engleski
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 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.
ultrasonic testing , anomaly detection , variational autoencoder , deep learning , computer vision
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
225-229.
2021.
objavljeno
10.1109/ISPA52656.2021.9552041
Podaci o matičnoj publikaciji
2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)
Institute of Electrical and Electronics Engineers (IEEE)
Podaci o skupu
12th International Symposium on Image and Signal Processing and Analysis (ISPA 2021)
predavanje
13.09.2021-15.09.2021
Zagreb, Hrvatska