Comparative analysis of median filter and its variants for removal of impulse noise from gray scale images

Anwar Shah, Javed Iqbal Bangash, Abdul Waheed Khan, Imran Ahmed, Abdullah Khan, Asfandyar Khan, Arshad Khan

Research output: Contribution to journalReview articlepeer-review

45 Citations (Scopus)

Abstract

Image denoising is a vital pre-processing phase, used to refine the image quality and make it more informative. Many image-denoising algorithms have been proposed with their own pros and cons. This paper presents a comprehensive study of the median filter and its different variants to reduce or remove the impulse noise from gray scale images. These filters are compared with respect to their functionality, time complexity and relative performance. For performance evaluation of the existing algorithms, extensive MATLAB based simulations have been carried out on a set of images. For benchmarking the relative performance, we have used Peak Signal to Noise Ratio (PSNR), Root Mean Square Error (RMSE), Universal Image Quality Index (UQI), Structural Similarity Index (SSIM) and Edge-strength Similarity (ESSIM) as quality assessment metrics. The Extended median filter (EMF) and Modified BDND are best in terms of relative statistical ratios and pleasant visual results where IAMF is having the best time complexity among existing algorithms.

Original languageEnglish
Pages (from-to)505-519
Number of pages15
JournalJournal of King Saud University - Computer and Information Sciences
Volume34
Issue number3
DOIs
Publication statusPublished - Mar 2022
Externally publishedYes

Keywords

  • Functionality
  • Image denoising
  • Impulse noise
  • Median filter
  • Pre-processing
  • Relative performance
  • Time complexity

Fingerprint

Dive into the research topics of 'Comparative analysis of median filter and its variants for removal of impulse noise from gray scale images'. Together they form a unique fingerprint.

Cite this