Reconstruction for Sparse View Tomography of Long Objects Applied to Imaging in the Wood Industry (2403.02820v1)
Abstract: In the wood industry, logs are commonly quality screened by discrete X-ray scans on a moving conveyor belt from a few source positions. Typically, two-dimensional (2D) slice-wise measurements are obtained by a sequential scanning geometry. Each 2D slice alone does not carry sufficient information for a three-dimensional tomographic reconstruction in which biological features of interest in the log are well preserved. In the present work, we propose a learned iterative reconstruction method based on the Learned Primal-Dual neural network, suited for sequential scanning geometries. Our method accumulates information between neighbouring slices, instead of only accounting for single slices during reconstruction. Our quantitative and qualitative evaluations with as few as five source positions show that our method yields reconstructions of logs that are sufficiently accurate to identify biological features like knots (branches), heartwood and sapwood.
- Operator discretization library (ODL), 2017.
- Task adapted reconstruction for inverse problems. Inverse Problems, 38(7):075006, 2022.
- Learned primal-dual reconstruction. IEEE Transactions on Medical Imaging, 37(6):1322–1332, 2018.
- Solving inverse problems using data-driven models. Acta Numerica, 28:1–174, 2019.
- A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging. Journal of mathematical imaging and vision, 40(1):120–145, 2011.
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences, 57(11):1413–1457, 2004.
- Industrial applications of computed tomography. CIRP annals, 63(2):655–677, 2014.
- David L Donoho. Compressed sensing. IEEE Transactions on information theory, 52(4):1289–1306, 2006.
- Computed tomography log scanning – high technology for forestry and forest based industry. Central European Forestry Journal, 65:51–59, 2019.
- The Swedish Stem Bank – A database for different silvicultural and wood properties. Technical report, Luleå University of Technology, Skellefteå, Sweden, 1995.
- Undersampled dynamic X-ray tomography with dimension reduction Kalman filter. IEEE Transactions on Computational Imaging, 5(3):492–501, 2019.
- Learning a variational network for reconstruction of accelerated MRI data. Magnetic resonance in medicine, 79(6):3055–3071, 2018.
- Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 26(9):4509–4522, 2017.
- Left-Ventricle Quantification Using Residual U-Net. In Mihaela Pop, Maxime Sermesant, Jichao Zhao, Shuo Li, Kristin McLeod, Alistair Young, Kawal Rhode, and Tommaso Mansi, editors, Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges, pages 371–380, Cham, 2019. Springer International Publishing.
- Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing. IEEE Signal Processing Magazine, 38(2):18–44, 2021.
- Automatic differentiation in PyTorch. In 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017.
- Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena, 60(1-4):259–268, 1992.
- 3D helical CT Reconstruction with a Memory Efficient Learned Primal-Dual Architecture. arXiv e-prints, pages arXiv–2205, 2022.
- Invertible Learned Primal-Dual. In NeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021.
- Reconstruction and segmentation from sparse sequential X-ray measurements of wood logs. arXiv preprint arXiv:2206.09595, 2022.
- Stochastic primal-dual deep unrolling. arXiv preprint arXiv:2110.10093, 2021.
- The MONAI Consortium. Project MONAI, December 2020.
- A Fast and Continuous CT scanner for the optimization of logs in a sawmill. In 8th Conference on Industrial Computed Tomography (iCT) 2018, volume 23, Wels, Austria, February 2018. e-Journal of Nondestructive Testing.
- Fast and flexible X-ray tomography using the ASTRA toolbox. Optics express, 24(22):25129–25147, 2016.
- Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.