Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-554598
Learned block iterative shrinkage thresholding algorithm for photothermal super resolution imaging
- Block-sparse regularization is already well known in active thermal imaging and is used for multiple-measurement-based inverse problems. The main bottleneck of this method is the choice of regularization parameters which differs for each experiment. We show the benefits of using a learned block iterative shrinkage thresholding algorithm (LBISTA) that is able to learn the choice of regularization parameters, without the need to manually select them. In addition, LBISTA enables the determination of a suitable weight matrix to solve the underlying inverse problem. Therefore, in this paper we present LBISTA and compare it with state-of-the-art block iterative shrinkage thresholding using synthetically generated and experimental test data from active thermography for defect reconstruction. Our results show that the use of the learned block-sparse optimization approach provides smaller normalized mean square errors for a small fixed number of iterations. Thus, this allows us to improve theBlock-sparse regularization is already well known in active thermal imaging and is used for multiple-measurement-based inverse problems. The main bottleneck of this method is the choice of regularization parameters which differs for each experiment. We show the benefits of using a learned block iterative shrinkage thresholding algorithm (LBISTA) that is able to learn the choice of regularization parameters, without the need to manually select them. In addition, LBISTA enables the determination of a suitable weight matrix to solve the underlying inverse problem. Therefore, in this paper we present LBISTA and compare it with state-of-the-art block iterative shrinkage thresholding using synthetically generated and experimental test data from active thermography for defect reconstruction. Our results show that the use of the learned block-sparse optimization approach provides smaller normalized mean square errors for a small fixed number of iterations. Thus, this allows us to improve the convergence speed and only needs a few iterations to generate accurate defect reconstruction in photothermal super-resolution imaging.…
Autor*innen: | J. C. Hauffen, L. Kästner, Samim AhmadiORCiD, P. Jung, G. Caire, Mathias ZieglerORCiD |
---|---|
Dokumenttyp: | Zeitschriftenartikel |
Veröffentlichungsform: | Verlagsliteratur |
Sprache: | Englisch |
Titel des übergeordneten Werkes (Englisch): | Sensors |
Jahr der Erstveröffentlichung: | 2022 |
Organisationseinheit der BAM: | 8 Zerstörungsfreie Prüfung |
8 Zerstörungsfreie Prüfung / 8.0 Abteilungsleitung und andere | |
Veröffentlichende Institution: | Bundesanstalt für Materialforschung und -prüfung (BAM) |
Verlag: | MDPI |
Verlagsort: | Basel |
Jahrgang/Band: | 22 |
Ausgabe/Heft: | 15 |
Aufsatznummer: | 5533 |
Erste Seite: | 1 |
Letzte Seite: | 15 |
DDC-Klassifikation: | Naturwissenschaften und Mathematik / Chemie / Analytische Chemie |
Freie Schlagwörter: | Active thermal imaging; Block-sparsity; Defect reconstruction; Laser; Laser thermography; Machine learning; NDT; Neural network; Non-destructive testing; Optimization; Regularization; Thermography |
Themenfelder/Aktivitätsfelder der BAM: | Chemie und Prozesstechnik |
DOI: | 10.3390/s22155533 |
URN: | urn:nbn:de:kobv:b43-554598 |
ISSN: | 1424-8220 |
Zugehöriger Identifikator: | https://nbn-resolving.org/urn:nbn:de:kobv:b43-525364 |
Verfügbarkeit des Dokuments: | Datei für die Öffentlichkeit verfügbar ("Open Access") |
Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |
Datum der Freischaltung: | 10.08.2022 |
Referierte Publikation: | Ja |
Datum der Eintragung als referierte Publikation: | 10.08.2022 |
Schriftenreihen ohne Nummerierung: | Wissenschaftliche Artikel der BAM |