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

Luming Liang, Seng Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin

Research output: Journal article publicationJournal articleAcademic researchpeer-review

18 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)26-35
Number of pages10
JournalNeurocomputing
Volume442
DOIs
Publication statusPublished - 28 Jun 2021

Keywords

  • Deep neural network
  • Image processing
  • Median layer
  • Salt-and-pepper noise

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Convolutional neural network with median layers for denoising salt-and-pepper contaminations'. Together they form a unique fingerprint.

Cite this