Fast detection and removal of impulsive noise using peer groups and fuzzy metrics

  • Authors:

  • Joan-Gerard Camarena;Valentín Gregori;Samuel Morillas;Almanzor Sapena

  • Affiliations:

  • Universidad Politécnica de Valencia, E.P.S. Gandia, Carretera Nazaret-Oliva s/n, 46730 Grau de Gandia, Valencia, Spain;Universidad Politécnica de Valencia, E.P.S. Gandia, Carretera Nazaret-Oliva s/n, 46730 Grau de Gandia, Valencia, Spain;Universidad Politécnica de Valencia, E.P.S. Gandia, Carretera Nazaret-Oliva s/n, 46730 Grau de Gandia, Valencia, Spain;Universidad Politécnica de Valencia, E.P.S. Gandia, Carretera Nazaret-Oliva s/n, 46730 Grau de Gandia, Valencia, Spain

  • Venue:
  • Journal of Visual Communication and Image Representation
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

A novel approach to impulsive noise detection in color images is introduced. In the paper, the peer group concept is redefined by means of a certain fuzzy metric. This concept is employed for the fast detection of noisy pixels by taking advantage of the fuzzy metric properties. On the basis of the noisy pixel detection a switching filter between the arithmetic mean filter (AMF) and the identity operation is proposed. The proposed switching filter achieves a trade-off between noise suppression and signal-detail preservation and is faster than recently introduced switching filters based on the peer group concept.