一种基于脉冲噪声检测的图像去噪方法

针对标准中值滤波在去除强噪声时存在的不足,提出一种改进的去噪方法.该方法通过多尺度窗口对图像脉冲噪声进行检测,其中判断噪声点的阈值可由图像中不同区域的灰度值自适应地调整,然后根据检测结果进行选择性滤波.该方法可以有效滤除图像中的脉冲噪声,又能较好的保持图像的边缘细节,尤其在强噪声情况下的效果更为明显.最后给出了滤波实验的仿真结果,说明了该方法的有效性.

An Image De - noising Algorithm Based on Detection of Impulse Noise

To overcome the drawbacks of the standard median filter in eliminating strong noise, an improved de-noising algorithm is proposed in this paper. It first detects impulse noise in an image by multiplex scale window, and the threshold can be modified adaptively according to the brightness value of different regions. Modified median filtering based on the noise detection results is adopted to remove the impulse noise. This method can effectively remove the impulse noise while successfully preserving the image edge details. It is very worthy in bad noise. The filtering result by experiments is given and it testifies the effectiveness of the algorithm.