Sparse View Tomographic Reconstruction of Elongated Objects using Learned Primal-Dual Networks
This addresses a domain-specific problem for the wood industry by enabling better quality screening of logs, but it is incremental as it adapts an existing learned primal-dual network to a specific scanning geometry.
The paper tackled the problem of reconstructing 3D tomographic images of logs from sparse X-ray scans in the wood industry, and the result was that their method achieved sufficiently accurate reconstructions to identify biological features like knots, heartwood, and sapwood with as few as five source positions.
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, the measurements are obtained in a single two-dimensional (2D) plane (a "slice") by a sequential scanning geometry. The data from each 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. Evaluations were performed by training U-Nets on segmentation of knots (branches), which are crucial features in wood processing. Our quantitative and qualitative evaluations show that with as few as five source positions our method yields reconstructions of logs that are sufficiently accurate to identify biological features like knots (branches), heartwood and sapwood.