提出一种两步式椒盐噪声去除方法.第一步利用自适应中值滤波器来识别出被噪声污染的候选点;第二步利用一种边缘保持技术(全变差图像修复)来恢复出被噪声污染的点.由于椒盐噪声点的灰度值和原始像素灰度独立,所以在采用恢复技术时不使用噪声点自身的灰度信息.在噪声率不很高的情况下,这种方法可以获得比现有最好方法更高的信噪比;当噪声率高达70%以上时,该方法的信噪比与现有方法非常接近,但是主观视觉效果(例如边缘保持能力)更佳. A two-step salt-and-pepper noise removal method is proposed.Firstly, an adaptive median filter is used to identify noise-contaminated candidate points. In the second step, an edge-preserving technique (total variation image restoration) Noise pollution point.As the salt and pepper noise point of the gray value and the original pixel gray, so the use of recovery techniques do not use the noise point of their own gray-level information.In the case of low noise rate, this method The signal to noise ratio of this method is very close to the existing method when the noise rate is more than 70%, but the subjective visual effects (such as the edge retention ability) are better.