一种基于去噪阈值的数字图像混合去噪算法

A Mixed De-noising Algorithm of Digital Image Based on Removed-noise Threshold

提出了一种效果良好的基于去噪阈值的数字图像混合去噪算法。提出了模糊相邻度和去噪阈值的概念,采用加权平均来取代传统的绝对平均值,把相邻度设为像素的权值,把传统的点对点处用点对块处理来取代,采用去噪阈值取代传统的阈值,因而用所提出方法处理过的图像更加清晰。实验结果显示,该算法比基于传统平滑算法的去噪效果更佳。

An efficient mixed de-nosing algorithm of digital image based on removed-nosie threshold is presented. The conception of neighborhood and removed-noise substituted for introduced. The weight average is substituted for traditional average operation, which is assigned as weight value. This algorithm also advances pixel-bloek operation instead of pixel-pixel operation and removed-noise threshold instead of segmentation threshold, which causes the image more explicit and shows obvious superiority especially when the noise is more complex. Results show that the approach based on fuzzy smoothing approach provides a powerful noise removal ability than the classical ones.