Quantifying the effect of X-ray scattering for data generation in real-time defect detection

Journal of X-Ray Science and Technology, vol. 32, pp. 1099–1119

Abstract

BACKGROUND: X-ray imaging is widely used for the non-destructive detection of defects in industrial products on a conveyor belt. In-line detection requires highly accurate, robust, and fast algorithms. Deep Convolutional Neural Networks (DCNNs) satisfy these requirements when a large amount of labeled data is available. To overcome the challenge of collecting these data, different methods of X-ray image generation are considered. OBJECTIVE: Depending on the desired degree of similarity to real data, different physical effects should either be simulated or can be ignored. X-ray scattering is known to be computationally expensive to simulate, and this effect can greatly affect the accuracy of a generated X-ray image. We aim to quantitatively evaluate the effect of scattering on defect detection. METHODS: Monte-Carlo simulation is used to generate X-ray scattering distribution. DCNNs are trained on the data with and without scattering and applied to the same test datasets. Probability of Detection (POD) curves are computed to compare their performance, characterized by the size of the smallest detectable defect. RESULTS: We apply the methodology to a model problem of defect detection in cylinders. When trained on data without scattering, DCNNs reliably detect defects larger than 1.3 mm, and using data with scattering improves performance by less than 5%. If the analysis is performed on the cases with large scattering-to-primary ratio (1 < SPR < 5), the difference in performance could reach 15% (approx. 0.4 mm). CONCLUSION: Excluding the scattering signal from the training data has the largest effect on the smallest detectable defects, and the difference decreases for larger defects. The scattering-to-primary ratio has a significant effect on detection performance and the required accuracy of data generation.

Authors 4

1. Vladyslav Andriiashen corresponding

   Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde en Informatica, Amsterdam, The Netherlands

2. Robert van Liere

   Centrum Wiskunde & Informatica · Eindhoven University of Technology

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde en Informatica, Amsterdam, The Netherlands

   Faculteit Wiskunde en Informatica, Technical University Eindhoven, Eindhoven, The Netherlands

3. Tristan van Leeuwen

   Centrum Wiskunde & Informatica · Utrecht University

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde en Informatica, Amsterdam, The Netherlands

   Mathematical Institute, Utrecht University, Utrecht, The Netherlands

4. Kees Joost Batenburg Aachen Leiden Institute of Advanced Computer Science

   Leiden University · Centrum Wiskunde & Informatica

   Affiliation as printed

   Computational Imaging, Centrum Wiskunde en Informatica, Amsterdam, The Netherlands

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