Filtern
Dokumenttyp
Sprache
- Englisch (3)
Referierte Publikation
- ja (3)
Schlagworte
- Defect reconstruction (3) (entfernen)
Organisationseinheit der BAM
This article presents deep unfolding neural networks to handle inverse problems in photothermal radiometry enabling super-resolution (SR) imaging. The photothermal SR approach is a well-known technique to overcome the spatial resolution limitation in photothermal imaging by extracting high-frequency spatial components based on the deconvolution with the thermal point spread function (PSF). However, stable deconvolution can only be achieved by using the sparse structure of defect patterns, which often requires tedious, handcrafted tuning of hyperparameters and results in computationally intensive algorithms. On this account, this article proposes Photothermal-SR-Net, which performs deconvolution by deep unfolding considering the underlying physics. Since defects appear sparsely in materials, our approach includes trained block-sparsity thresholding in each convolutional layer. This enables to super-resolve 2-D thermal images for nondestructive testing (NDT) with a substantially improved convergence rate compared to classic approaches. The performance of the proposed approach is evaluated on various deep unfolding and thresholding approaches. Furthermore, we explored how to increase the reconstruction quality and the computational performance. 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.
Learned block iterative shrinkage thresholding algorithm for photothermal super resolution imaging
(2022)
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.
This paper presents different super resolution reconstruction techniques to overcome the spatial resolution limits in thermography. Pseudo-random blind structured illumination from a onedimensional laser array is used as heat source for super resolution thermography. Pulsed thermography measurements using an infrared camera with a high frame rate sampling lead to a huge amount of data. To handle this large data set, thermographic reconstruction techniques are an essential step of the overall reconstruction process. Four different thermographic reconstruction techniques are analyzed based on the Fourier transform amplitude, principal component analysis, virtual wave reconstruction and the maximum thermogram. The application of those methods results in a sparse basis representation of the measured data and serves as input for a compressed sensing based algorithm called iterative joint sparsity (IJOSP). Since the thermographic reconstruction techniques have a high influence on the result of the IJOSP algorithm, this paper Highlights their Advantages and disadvantages.