Title: An adaptive minimum-maximum value-based weighted median filter for removing high density salt and pepper noise in medical images
Authors: Bharat Garg
Addresses: Thapar Institute of Engineering and Technology Patiala, Punjab, India
Abstract: This paper presents an adaptive minimum-maximum value-based weighted median (AMMWM) filter that effectively restores noisy pixel in medical images at high noise density. The proposed filter computes two highly correlated groups of noise-free pixels using minimum and maximum value of the current window. Further, weighted medians of these groups determine the estimated value of candidate noisy pixel. If the current window fails to provide any noise-free pixels, its size is increased by one. The maximum size of window considered is 7 × 7 to minimise blurring. The proposed AMMWM filter is evaluated on various medical images where it provides higher quality metrics while preserving image features even at higher noise density. The simulation results using X-ray images show on an average 0.3 dB and 3.56 dB higher value of PSNR for wide (10%-90%) and very high (91%-98%) noise density ranges respectively.
Keywords: salt-and-pepper noise; median filter; mean filter; nonlinear filter; image processing.
DOI: 10.1504/IJAHUC.2020.109795
International Journal of Ad Hoc and Ubiquitous Computing, 2020 Vol.35 No.2, pp.84 - 95
Received: 20 Apr 2020
Accepted: 24 Apr 2020
Published online: 24 Sep 2020 *