Removing of Salt-and-pepper Noise in Images Based on Adaptive Median Filtering and Improved Threshold Function
Ying Qian · 2019
AMF-WT algorithm, based on adaptive median filtering and an improved threshold function, is proposed in this paper. After salt-and-pepper noise is removed from the image by adaptive median filtering, two-level wavelet decomposition is done on the image. The high frequency coefficients are denoised with the improved threshold function designed in this paper, then reconstructed with low frequency coefficients. MATLAB simulations show that AMF-WT algorithm is superior to adaptive median filter and median filter in eliminating salt-and-pepper noise. The improved threshold function designed has better denoising effect than hard threshold function and soft threshold function. AMF-WT algorithm can be applied to practical image denoising.