A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging

e-Journal of Nondestructive Testing, vol. 30

Abstract

X-ray computed tomography (CT) is a powerful imaging tool for defect detection, segmentation and feature extraction in industrial applications as it enables non-destructive evaluation. The presence of artifacts and noise, however, imposes difficulties on the defect detection due to low contrast between defects and material. Different methods, the most recent ones based on deep learning, have been proposed to address both CT artifacts and noise. In this work, three state-of-the-art denoising techniques, namely BM3D, a supervised UNet and Noise2Inverse are compared with a novel approach based on a set of CNNs applied at different stages of the CT data acquisition pipeline. The comparison is done regarding the capabilities of the methods in terms of image quality enhancement as a preprocessing step in CT-based data analysis before performing defect segmentation.

Authors 11

1. Virginia Florian

   Fraunhofer Institute for Integrated Circuits

   Affiliation as printed

   Fraunhofer Institute of Integrated Circuits IIS , Division Development Center X-ray Technology , Flugplatzstr. 75 , Fürth , 90768 , Germany

2. Jiayang Shi Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden Universiteit , Leiden , The Netherlands

3. Willem Jan Palestijn
4. Daniël M. Pelt Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden Universiteit , Leiden , The Netherlands

5. K. Joost Batenburg Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden Universiteit , Leiden , The Netherlands

6. Thomas Lang

   Fraunhofer Institute for Integrated Circuits

   Affiliation as printed

   Fraunhofer Institute of Integrated Circuits IIS , Division Development Center X-ray Technology , Flugplatzstr. 75 , Fürth , 90768 , Germany

7. Christoph Heinzl

   University of Passau · Fraunhofer Institute for Integrated Circuits

   Affiliation as printed

   Fraunhofer Institute of Integrated Circuits IIS , Division Development Center X-ray Technology , Flugplatzstr. 75 , Fürth , 90768 , Germany

   University of Passau , Innstraße 43 , Passau , Germany

8. Christian Kretzer

   Fraunhofer Institute for Integrated Circuits

   Affiliation as printed

   Fraunhofer Institute of Integrated Circuits IIS , Division Development Center X-ray Technology , Flugplatzstr. 75 , Fürth , 90768 , Germany

9. Stefan Kasperl

   Fraunhofer Institute for Integrated Circuits

   Affiliation as printed

   Fraunhofer Institute of Integrated Circuits IIS , Division Development Center X-ray Technology , Flugplatzstr. 75 , Fürth , 90768 , Germany

10. Dominik Wolfschläger Aachen

    RWTH Aachen University

    Affiliation as printed

    WZL| RWTH Aachen University , Campus-Boulevard 30 , 52074 Aachen , Germany

11. Robert Heinrich Schmitt Aachen Fraunhofer IPT

    Fraunhofer Institute for Production Technology IPT · RWTH Aachen University

    Affiliation as printed

    Fraunhofer IPT , Steinbergstr. 17 , 52074 Aachen , Germany

    WZL| RWTH Aachen University , Campus-Boulevard 30 , 52074 Aachen , Germany