TY - JOUR A1 - Hauffen, J. C. A1 - Kästner, L. A1 - Ahmadi, Samim A1 - Jung, P. A1 - Caire, G. A1 - Ziegler, Mathias T1 - Learned block iterative shrinkage thresholding algorithm for photothermal super resolution imaging JF - Sensors N2 - 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 the convergence speed and only needs a few iterations to generate accurate defect reconstruction in photothermal super-resolution imaging. KW - Thermography KW - Laser KW - Machine learning KW - Optimization KW - Non-destructive testing KW - NDT KW - Neural network KW - Defect reconstruction KW - Block-sparsity KW - Active thermal imaging KW - Regularization KW - Laser thermography PY - 2022 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-554598 DO - https://doi.org/10.3390/s22155533 SN - 1424-8220 VL - 22 IS - 15 SP - 1 EP - 15 PB - MDPI CY - Basel AN - OPUS4-55459 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -