Convolutional neural network with median layers for denoising salt-and-pepper contaminations

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully conv...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2021-06, Vol.442, p.26-35
Main Authors: Liang, Luming, Deng, Seng, Gueguen, Lionel, Wei, Mingqiang, Wu, Xinming, Qin, Jing
Format: Article
Language:English
Subjects:
Deep neural network
Image processing
Median layer
Salt-and-pepper noise
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes extremely high-level s&p noise without performing any non-trivial preprocessing tasks. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.02.010