Efficient impulse noise reduction via local directional gradients and fuzzy logic

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

This paper proposes an efficient noise reduction method for image restoration. A novel pixel classification method by using fuzzy logic and local gradients is first introduced to discriminate noise and noise-free pixels from corrupted images. Then, a switching filtering scheme is employed to noisy images. The noise pixels will be filtered by a weighted median filter with adaptive weights when the noise-free pixels are preserved in the filtered images. Both numerical comparisons and perceptual observations are demonstrated in the experimental simulations. It is found that the proposed method achieves a fairly better performance than a number of other existing methods in noise reduction and image restoration.

Original languageEnglish
Pages (from-to)1841-1857
Number of pages17
JournalFuzzy Sets and Systems
Volume160
Issue number13
DOIs
StatePublished - 1 Jul 2009

Keywords

  • Fuzzy logic
  • Fuzzy systems
  • Image restoration
  • Noise detection
  • Noise reduction

Fingerprint

Dive into the research topics of 'Efficient impulse noise reduction via local directional gradients and fuzzy logic'. Together they form a unique fingerprint.

Cite this