Abstract: A new method of mixed noise removal for digital image is presented in the paper，combing adaptive median filter and adaptive compressed weighted mean filter.The min-max operator is used to detect impulse noise and remove the impulse noise with adaptive median filter.An adaptive compressed weighted mean filter is used to filter Gaussian noise.Lots of experiments show that the method can remove mixed impulse and Gaussian noise efficiently while protecting image details.

Key words: image procession, adaptive median, compressed weighted mean, mixed noise

摘要： 结合自适应中值滤波技术和自适应压缩加权均值滤波技术，提出了一种新的图像混合噪声滤波算法。算法首先对受混合噪声污染的图像利用灰度极值检测出脉冲噪声，运用自适应中值滤波滤除脉冲噪声；其次对处理结果进行自适应压缩的加权均值滤波。实验结果说明算法不仅能有效地滤除脉冲与高斯混合噪声，而且可以较好地保护图像细节。

关键词: 图像处理, 自适应中值, 压缩加权均值, 混合噪声