A new adaptive weighted mean filter for removing high density impulse noise
Zhiyong Tang, Zhenji Yang, Kun Liu, Zhongcai Pei · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2016
In this article, a new adaptive weighted mean filter is proposed to detect and remove high density impulse noise in digital images. The proposed method consists of detecting stage and filtering stage. In the detecting stage, all pixels are labeled based on the proposed classification principle. Besides, all pixels are set with different weights, which are used to confirm the size of the sliding window. In filtering stage, a new weighted mean filter synthesizes both the information of center pixel and the relationship of all the pixels in the sliding window. Hence, the center pixel, labeled “the noise-free pixel” remains unchanged. The “noise-like pixels” and “clear-like pixels” are replaced by the weighted mean of the current window. The simulation result shows that the performance of the proposed filter is better than some existing methods, both in vision and quantitative measurements.