一种混合噪声的模糊滤波算法  

Fuzzy Denoising Algorithm for Mixed Noise

作　　者：董鸿燕[1] 张焱[2] 沈振康[2] 

机构地区：[1]通信指挥学院信息作战教研室,武汉430010 [2]国防科技大学ATR重点实验室,长沙410073

出　　处：《系统仿真学报》2009年第10期2832-2835,共4页Journal of System Simulation

基　　金：武器装备预研基金项目(51483020105ZS9309)

摘　　要：为了解决混合噪声图像增强中抑制噪声和保持边缘细节的矛盾,提出一种基于多级中值滤波和模糊加权均值滤波的图像模糊去噪方法。根据不同的区域,不同噪声,通过模糊推理,模糊合成多级中值滤波和模糊加权均值滤波的结果,在滤除混合噪声的同时,保留图像的边缘细节。根据实验结果,从客观和主观两方面比较了本算法和几种方法的效果,表明本方法有较好的抑制噪声,保持图像细节对比度的能力。A new image denoising method aimed at removing mixed noise while preserving edges was proposed based on multistage median filtering and fuzzy weighted averaging filtering. For different area and different kind of noise, multistage median filter and fuzzy weighted averaging filter was used. Then the result of different filter was synthesized by fuzzy inference. Compared with several algorithms in subjective aspect and objective aspect, experiments show that this method can do better in smoothing mixed noise and preserving edges.

关 键 词：多级中值滤波 去噪 隶属度函数 模糊推理 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]