satoshi ITO1, taro SUGAI1, kohei TAKANO1, and shohei OUCHI1
1Utsunomiya University, Utsunomiya, Japan
1Utsunomiya University, Utsunomiya, Japan
Parallelized blind CNN denoising for linearly combined noisy sliced images was proposed. Experimental
studies showed that the PSNR and the SSIM were improved for noise levels, from
2.5% to 7.5%. Greatest PSNR improvements were obtained when three slice images
were used.
Figure 1. Schematic of parallelized blind image denoising (ParBID).
The first step is the linear combination of
adjacent images with given weights $$$a$$$.
The second step is the blind DnCNN of the combined images. The third step is
the separation of linearly combined images by solving linear equations.
Figure 3. Denoised image with
ParBID in BDnCNN. Original image is shown in (a), and target noisy image is
(c). The linear combination of adjacent images (b), (d) is shown in image (e).
Subimages (e) through (h) show the denoised images using single-slice BDnCNN
and the 2- and 3-slice ParBID using BDnCNN. Subimages (i) through (n) are the
enlarged images.