Zitieren Sie bitte immer diese URN: urn:nbn:de:kobv:b43-525371

Photothermal-SR-Net: A Customized Deep Unfolding Neural Network for Photothermal Super Resolution Imaging

  • This paper presents deep unfolding neural networks to handle inverse problems in photothermal radiometry enabling super resolution (SR) imaging. Photothermal imaging is a well-known technique in active thermography for nondestructive inspection of defects in materials such as metals or composites. A grand challenge of active thermography is to overcome the spatial resolution limitation imposed by heat diffusion in order to accurately resolve each defect. The photothermal SR approach enables to extract high-frequency spatial components based on the deconvolution with the thermal point spread function. However, stable deconvolution can only be achieved by using the sparse structure of defect patterns, which often requires tedious, hand-crafted tuning of hyperparameters and results in computationally intensive algorithms. On this account, Photothermal-SR-Net is proposed in this paper, which performs deconvolution by deep unfolding considering the underlying physics. This enables to superThis paper presents deep unfolding neural networks to handle inverse problems in photothermal radiometry enabling super resolution (SR) imaging. Photothermal imaging is a well-known technique in active thermography for nondestructive inspection of defects in materials such as metals or composites. A grand challenge of active thermography is to overcome the spatial resolution limitation imposed by heat diffusion in order to accurately resolve each defect. The photothermal SR approach enables to extract high-frequency spatial components based on the deconvolution with the thermal point spread function. However, stable deconvolution can only be achieved by using the sparse structure of defect patterns, which often requires tedious, hand-crafted tuning of hyperparameters and results in computationally intensive algorithms. On this account, Photothermal-SR-Net is proposed in this paper, which performs deconvolution by deep unfolding considering the underlying physics. This enables to super resolve 2D thermal images for nondestructive testing with a substantially improved convergence rate. Since defects appear sparsely in materials, Photothermal-SR-Net applies trained blocksparsity thresholding to the acquired thermal images in each convolutional layer. The performance of the proposed approach is evaluated and discussed using various deep unfolding and thresholding approaches applied to 2D thermal images. Subsequently, studies are conducted on how to increase the reconstruction quality and the computational performance of Photothermal-SR-Net is evaluated. Thereby, it was found that the computing time for creating high-resolution images could be significantly reduced without decreasing the reconstruction quality by using pixel binning as a preprocessing step.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Teilen auf Twitter Suche bei Google Scholar
Metadaten
Autoren/innen:Samim Ahmadi, L. Kästner, Jan Christian Hauffen, P. Jung, Mathias Ziegler
Dokumenttyp:Sonstiges
Veröffentlichungsform:Graue Literatur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):arxiv.org
Jahr der Erstveröffentlichung:2021
Organisationseinheit der BAM:8 Zerstörungsfreie Prüfung
8 Zerstörungsfreie Prüfung / 8.7 Thermografische Verfahren
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:Cornell University
Verlagsort:New York
Erste Seite:arXiv:2104.10563
DDC-Klassifikation:Naturwissenschaften und Mathematik / Chemie / Analytische Chemie
Freie Schlagwörter:Deep imaging; Deep learning; Deep unfolding; Elastic net; Iterative shrinkage thresholding algorithm; Laser thermography; Nondestructive testing; Photothermal super resolution; Physics-based deep learning
Themenfelder/Aktivitätsfelder der BAM:Analytical Sciences
Analytical Sciences / Zerstörungsfreie Prüfung und Spektroskopie
URN:urn:nbn:de:kobv:b43-525371
URL:https://arxiv.org/abs/2104.10563
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Datum der Freischaltung:29.04.2021
Referierte Publikation:Nein
Schriftenreihen ohne Nummerierung:Arbeitspapiere der BAM