تقرير
Quantifying the effect of X-ray scattering for data generation in real-time defect detection
| العنوان: | Quantifying the effect of X-ray scattering for data generation in real-time defect detection |
|---|---|
| المؤلفون: | Andriiashen, Vladyslav, van Liere, Robert, van Leeuwen, Tristan, Batenburg, K. Joost |
| المصدر: | Journal of X-Ray Science and Technology, vol. 32, no. 4, pp. 1099-1119, 2024 |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
| الوصف: | 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. Comment: This paper appears in: Journal of X-Ray Science and Technology, vol. 32, no. 4, pp. 1099-1119, 2024. Print ISSN: 0895-3996 Online ISSN: 1095-9114 Digital Object Identifier: https://doi.org/10.3233/XST-230389 |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.3233/XST-230389 |
| URL الوصول: | http://arxiv.org/abs/2305.12822 |
| رقم الأكسشن: | edsarx.2305.12822 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.3233/XST-230389 |
|---|