Vector median filter based on non-causal linear prediction for detection of impulse noise from images

  • Authors:

  • Khumanthem Manglem Singh

  • Affiliations:

  • Department of Computer Science and Engineering, National Institute of Technology Manipur, Imphal - 795001, India

  • Venue:
  • International Journal of Computational Science and Engineering
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

A new switching vector median filter based on the non-causal linear prediction for the detection of impulse noise from colour images is presented. The proposed filter utilises non-causal linear prediction coefficients obtained from the block-by-block autocorrelation function to find prediction error by taking difference between the vector pixel value at the centre of the filter window and predicted vector pixel value at that location. The vector pixel at the centre of the filter window is replaced by vector median if the error is bigger than a pre-defined threshold. Extensive simulation experiments indicate that the new vector median filter outperforms the vector median filter as well as other techniques currently used to eliminate impulse noise from colour images.