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

Journal of King Saud University: Computer and Information Sciences

Abdul Waheed Khan¹  Abdullah Khan²  Anwar Shah³  Arshad Khan⁴  Javed Iqbal Bangash⁴  Asfandyar Khan⁴  Imran Ahmed⁵ 

[1] Corresponding author.;Centre of Excellence in IT, Institute of Management Sciences, Peshawar, KPK, Pakistan;Department of Computer Science, FAST-National University of Computer and Emerging Sciences (NUCES), Peshawar Campus, KPK, Pakistan;Institute of Computer Sciences and IT, The University of Agriculture Peshawar, KPK, Pakistan;School of Computing, FAST-National University of Computer and Emerging Sciences (NUCES), Islamabad Campus, Pakistan;

关键词: Image denoising;    Pre-processing;    Impulse noise;    Median filter;    Functionality;    Time complexity;   

DOI  :  

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown