Neural network Hilbert transform based filtered backprojection for fast inline x-ray inspection
- Author
- Eline Janssens, Jan De Beenhouwer, Mattias Van Dael, Thomas De Schryver (UGent) , Luc Van Hoorebeke (UGent) , Pieter Verboven, Bart Nicolai and Jan Sijbers
- Organization
- Project
- Abstract
- X-ray imaging is an important tool for quality control since it allows to inspect the interior of products in a non-destructive way. Conventional x-ray imaging, however, is slow and expensive. Inline x-ray inspection, on the other hand, can pave the way towards fast and individual quality control, provided that a sufficiently high throughput can be achieved at a minimal cost. To meet these criteria, an inline inspection acquisition geometry is proposed where the object moves and rotates on a conveyor belt while it passes a fixed source and detector. Moreover, for this acquisition geometry, a new neural-network-based reconstruction algorithm is introduced: the neural network Hilbert transform based filtered backprojection. The proposed algorithm is evaluated both on simulated and real inline x-ray data and has shown to generate high quality reconstructions of 400 x 400 reconstruction pixels within 200 ms, thereby meeting the high throughput criteria.
- Keywords
- inline inspection, x-ray tomography, filtered backprojection, ELECTRON TOMOGRAPHY, ASTRA TOOLBOX, RECONSTRUCTION, ALGORITHM
Downloads
-
Janssens 2018 Meas. Sci. Technol. 29 034012.pdf
- full text
- |
- open access
- |
- |
- 3.39 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8551475
- MLA
- Janssens, Eline, et al. “Neural Network Hilbert Transform Based Filtered Backprojection for Fast Inline X-Ray Inspection.” MEASUREMENT SCIENCE AND TECHNOLOGY, vol. 29, no. 3, 2018, doi:10.1088/1361-6501/aa9de3.
- APA
- Janssens, E., De Beenhouwer, J., Van Dael, M., De Schryver, T., Van Hoorebeke, L., Verboven, P., … Sijbers, J. (2018). Neural network Hilbert transform based filtered backprojection for fast inline x-ray inspection. MEASUREMENT SCIENCE AND TECHNOLOGY, 29(3). https://doi.org/10.1088/1361-6501/aa9de3
- Chicago author-date
- Janssens, Eline, Jan De Beenhouwer, Mattias Van Dael, Thomas De Schryver, Luc Van Hoorebeke, Pieter Verboven, Bart Nicolai, and Jan Sijbers. 2018. “Neural Network Hilbert Transform Based Filtered Backprojection for Fast Inline X-Ray Inspection.” MEASUREMENT SCIENCE AND TECHNOLOGY 29 (3). https://doi.org/10.1088/1361-6501/aa9de3.
- Chicago author-date (all authors)
- Janssens, Eline, Jan De Beenhouwer, Mattias Van Dael, Thomas De Schryver, Luc Van Hoorebeke, Pieter Verboven, Bart Nicolai, and Jan Sijbers. 2018. “Neural Network Hilbert Transform Based Filtered Backprojection for Fast Inline X-Ray Inspection.” MEASUREMENT SCIENCE AND TECHNOLOGY 29 (3). doi:10.1088/1361-6501/aa9de3.
- Vancouver
- 1.Janssens E, De Beenhouwer J, Van Dael M, De Schryver T, Van Hoorebeke L, Verboven P, et al. Neural network Hilbert transform based filtered backprojection for fast inline x-ray inspection. MEASUREMENT SCIENCE AND TECHNOLOGY. 2018;29(3).
- IEEE
- [1]E. Janssens et al., “Neural network Hilbert transform based filtered backprojection for fast inline x-ray inspection,” MEASUREMENT SCIENCE AND TECHNOLOGY, vol. 29, no. 3, 2018.
@article{8551475,
abstract = {{X-ray imaging is an important tool for quality control since it allows to inspect the interior of products in a non-destructive way. Conventional x-ray imaging, however, is slow and expensive. Inline x-ray inspection, on the other hand, can pave the way towards fast and individual quality control, provided that a sufficiently high throughput can be achieved at a minimal cost. To meet these criteria, an inline inspection acquisition geometry is proposed where the object moves and rotates on a conveyor belt while it passes a fixed source and detector. Moreover, for this acquisition geometry, a new neural-network-based reconstruction algorithm is introduced: the neural network Hilbert transform based filtered backprojection. The proposed algorithm is evaluated both on simulated and real inline x-ray data and has shown to generate high quality reconstructions of 400 x 400 reconstruction pixels within 200 ms, thereby meeting the high throughput criteria.}},
articleno = {{034012}},
author = {{Janssens, Eline and De Beenhouwer, Jan and Van Dael, Mattias and De Schryver, Thomas and Van Hoorebeke, Luc and Verboven, Pieter and Nicolai, Bart and Sijbers, Jan}},
issn = {{0957-0233}},
journal = {{MEASUREMENT SCIENCE AND TECHNOLOGY}},
keywords = {{inline inspection,x-ray tomography,filtered backprojection,ELECTRON TOMOGRAPHY,ASTRA TOOLBOX,RECONSTRUCTION,ALGORITHM}},
language = {{eng}},
number = {{3}},
pages = {{12}},
title = {{Neural network Hilbert transform based filtered backprojection for fast inline x-ray inspection}},
url = {{http://doi.org/10.1088/1361-6501/aa9de3}},
volume = {{29}},
year = {{2018}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: