view article
Figure 7
Demonstration of a potential other application of the CNN approach for ring artifacts correction. This case requires a different CNN architecture to transform the image from one style to another, which follows the same transformation rule as the training data. Image transformation of the Xlearn toolbox introduced in this article can be directly applied for this use. The top row shows the sinograms: (left) original, (middle) with added stripes, (right) stripes removed with CNN. The bottom row shows the corresponding reconstructions.

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 24| Part 2| March 2017| Pages 469-475
https://doi.org/10.1107/S1600577516020117
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS