GitHub - pandagre/Mixed-Noise-CNN: Codes for Mixed Noise Denoising using CNN

pandagre / Mixed-Noise-CNN Public

forked from tariqul-islam/Mixed-Noise-CNN

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Codes for Mixed Noise Denoising using CNN

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
FastTV2Phase		FastTV2Phase
Test_images		Test_images
models		models
.gitattributes		.gitattributes
.gitignore		.gitignore
CAI.m		CAI.m
ReadMe.txt		ReadMe.txt
acwmf.m		acwmf.m
adpmedft.m		adpmedft.m
butter_sign.mat		butter_sign.mat
butter_sign.png		butter_sign.png
denoiser_nn.py		denoiser_nn.py
denoiser_nn.pyc		denoiser_nn.pyc
impulsenoise.m		impulsenoise.m
psnr.py		psnr.py
psnr.pyc		psnr.pyc
sizeit.m		sizeit.m
test_cnn.py		test_cnn.py

Repository files navigation

The codes for removing mixed noise using small CNN. The codes are implementation of the paper:

Islam, M. T., Rahman, S. M., Ahmad, M. O., & Swamy, M. N. S. (2018). Mixed Gaussian-impulse noise reduction from images using convolutional neural network. Signal Processing: Image Communication.

Consider citing the paper if you find the codes useful.

In order to run the example you have to install numpy and tensorflow.

Instrucitons:

1. First run CAI.m to create Cai's method processed file.
2. Then run test_cnn.py to perform the denoising process.