基于模糊逻辑的脉冲噪声自适应滤除

为了去除具有多个随机值的普通脉冲噪声，提出一种基于模糊逻辑的自适应去噪方法。首先，利用像素邻域梯度并结合模糊逻辑相关理论进行噪声点初步检测；然后，通过噪声直方图统计对噪声点作二次检测，排除误判的噪声点；最后，保留非噪声点，对噪声点进行自适应加权均值滤波，滤除噪声。仿真结果表明，该算法可以取得优于传统方法的去噪效果，并且能很好地保护图像的边缘和纹理信息。

Impulse noise adaptive removal based on fuzzy logic

To remove the impulse noise with random values, this paper proposed an adaptive noise removal method based on fuzzy logic. Firstly, detected the noise pixels initially by the neighboring gradients of pixels and fuzzy logic theory. Secondly, detected the noise pixels secondarily by noise histogram statistics and excluded wrong noise pixels. Lastly, preserved the non-noise pixels and removed noise pixels by adaptive weighted mean filter. Simulation results show that the method can get better performance than traditional algorithms and it can preserve fine edges and texture details.