Cascaded decision-based median and un-symmetric trimmed mean filter for removal of high-density impulse noise in an image

  • Authors:

  • K. S. Srinivasan;D. Ebenezer

  • Affiliations:

  • Department of Electronics and Communication Engineering, College of Engineering, Guindy, Anna University, Chennai, India;Department of Electronics and Communication Engineering, College of Engineering, Guindy, Anna University, Chennai, India

  • Venue:
  • ICS'05 Proceedings of the 9th WSEAS International Conference on Systems
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

A new two-stage cascaded filtering algorithm is proposed for removal of high-density impulse noise. The first stage is the Decision-based Median Filter (DMF) which is used to identify pixels likely to be contaminated by impulsive noise and replaces them by the median value. The second stage is the Unsymmetric Trimmed Mean Filter (UTMF), which uses a small, fixed window, to trim the impulse values lying at the extreme ends, in an unsymmetric manner. The proposed algorithm is tested on different images and is found to produce better results, both in terms of visual appearance and quantitative measures. In terms of edge preservation and noise suppression, the proposed algorithm shows a significant improvement in comparison with other non-linear filters even if the noise density is as high as 90%.