A convolutional neural network for fast upsampling of undersampled tomograms in X-ray CT time-series using a representative highly sampled tomogram

Bellos, D.; Basham, M.; Pridmore, T.; French, A.P.

doi:10.1107/S1600577519003448

Journal of Synchrotron Radiation Journal of
Synchrotron Radiation

IUCr IT WDC

home archive editors for authors for readers submit subscribe open access

view article

Figure 3
Images of sinograms (the 1001st pixel row counting from the top for the real-world data, the 201th pixel row for the synthetic data) from the different datasets used in this paper. (A) From the real-world data used for training. (B) From the real-world data used for testing. (C) From the synthetic data used for training. (D) From the synthetic data used for testing. These sinograms correspond to the height where hydrogen bubbles are expected to be found. As can be seen in the real-world data, the sinograms suddenly stop (marker 1) as the bubbles surface on the top of the sample and pop. This was purposely avoided in the synthetic data in order to check the accuracy of our method when the conditions are nominal. The image ratio is different from the original for presentation purposes.

JOURNAL OF
SYNCHROTRON
RADIATION

ISSN: 1600-5775

Volume 26| Part 3| May 2019| Pages 839-853

https://doi.org/10.1107/S1600577519003448

Open

access

Follow J. Synchrotron Rad.

Search IUCr Journals		doi		Advanced search
Author		volume	page