Zhou Y, Schneider LS, Fan F, Maier A (2024)
Publication Status: Submitted
Publication Type: Conference contribution, Conference Contribution
Future Publication Type: Journal article
Publication year: 2024
DOI: 10.48550/arXiv.2401.16104
The rise of deep learning has introduced a transformative era in the field of image processing, particularly in the context of computed tomography. Deep learning has made a significant contribution to the field of industrial Computed Tomography. However, many defect detection algorithms are applied directly to the reconstructed domain, often disregarding the raw sensor data. This paper shifts the focus to the use of sinograms. Within this framework, we present a comprehensive three-step deep learning algorithm, designed to identify and analyze defects within objects without resorting to image reconstruction. These three steps are defect segmentation, mask isolation, and defect analysis. We use a U-Net-based architecture for defect segmentation. Our method achieves the Intersection over Union of 92.02% on our simulated data, with an average position error of 1.3 pixels for defect detection on a 512-pixel-wide detector.
APA:
Zhou, Y., Schneider, L.-S., Fan, F., & Maier, A. (2024). A 2D Sinogram-Based Approach to Defect Localization in Computed Tomography. In Proceedings of the CT Meeting 2024. Bamberg, DE.
MLA:
Zhou, Yuzhong, et al. "A 2D Sinogram-Based Approach to Defect Localization in Computed Tomography." Proceedings of the CT Meeting 2024, Bamberg 2024.
BibTeX: Download