<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>52537</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>10</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>preprint</type>
    <publisherName>Cornell University</publisherName>
    <publisherPlace>Ithaca, NY</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Photothermal-SR-Net: A customized deep unfolding neural network for photothermal super resolution imaging</title>
    <abstract language="eng">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 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.&#13;
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.</abstract>
    <parentTitle language="eng">arxiv.org</parentTitle>
    <identifier type="urn">urn:nbn:de:kobv:b43-525371</identifier>
    <identifier type="issn">2331-8422</identifier>
    <identifier type="doi">10.48550/arXiv.2104.10563</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="RelatedIdentifier">https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/54678</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Samim Ahmadi</author>
    <author>L. Kästner</author>
    <author>Jan Christian Hauffen</author>
    <author>P. Jung</author>
    <author>Mathias Ziegler</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Photothermal super resolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Nondestructive testing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep unfolding</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep imaging</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Physics-based deep learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Laser thermography</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Elastic net</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Iterative shrinkage thresholding algorithm</value>
    </subject>
    <collection role="ddc" number="543">Analytische Chemie</collection>
    <collection role="institutes" number="">8 Zerstörungsfreie Prüfung</collection>
    <collection role="institutes" number="">8.3 Thermografische Verfahren</collection>
    <collection role="themenfelder" number="">Chemie und Prozesstechnik</collection>
    <collection role="fulltextaccess" number="">Datei für die Öffentlichkeit verfügbar ("Open Access")</collection>
    <collection role="literaturgattung" number="">Graue Literatur</collection>
    <collection role="unnumberedseries" number="">Preprints der BAM</collection>
    <thesisPublisher>Bundesanstalt für Materialforschung und -prüfung (BAM)</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-bam/files/52537/2104.10563v1.pdf</file>
  </doc>
</export-example>
