view article
Figure 1
Data for training the DL network. (a) A simulated LabDCT image (Isimu) containing spots, a constant background and a central black area (pixel value = 0) from the sample D35. (b) A normalized background-noise image (IBG, gray values between 0 and 1) containing only long-range noise extracted from an experimental dataset. (c) An input image (x) containing both spots and noise. (d) A content image (yc) containing spots only.

IUCrJ
Volume 8| Part 5| September 2021| Pages 719-731
ISSN: 2052-2525
https://doi.org/10.1107/S2052252521005480