Multiplicative noise removal via a learned dictionary

Yu Mei Huang*, Lionel Moisan, Kwok Po Ng, Tieyong Zeng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

77 Citations (Scopus)


Multiplicative noise removal is a challenging image processing problem, and most existing methods are based on the maximum a posteriori formulation and the logarithmic transformation of multiplicative denoising problems into additive denoising problems. Sparse representations of images have shown to be efficient approaches for image recovery. Following this idea, in this paper, we propose to learn a dictionary from the logarithmic transformed image, and then to use it in a variational model built for noise removal. Extensive experimental results suggest that in terms of visual quality, peak signal-to-noise ratio, and mean absolute deviation error, the proposed algorithm outperforms state-of-the-art methods.

Original languageEnglish
Article number6220251
Pages (from-to)4534-4543
Number of pages10
JournalIEEE Transactions on Image Processing
Issue number11
Publication statusPublished - Nov 2012

Scopus Subject Areas

  • Software
  • Computer Graphics and Computer-Aided Design

User-Defined Keywords

  • Denoising
  • dictionary
  • multiplicative noise
  • sparse representation
  • variational model


Dive into the research topics of 'Multiplicative noise removal via a learned dictionary'. Together they form a unique fingerprint.

Cite this