多幅图像中值法在滤除噪声中的应用

Many Images Median Method in Application of Noise Filtering

数字图像在成像和传输过程中可能会夹杂一些噪声,如椒盐噪声和高斯噪声等。这些噪声可能会对图像处理结果产生消极影响,所以在图像处理前要对该图像进行平滑,因此提出了一种基于多幅图像中值的滤波方法。该算法首先对同一场景多次采集图像,然后将这些图像在相同位置上的灰度中值作为图像在该点的灰度值。为了验证算法的有效性进行了多次实验与传统算法比较,结果表明该算法不仅能最大程度地滤除椒盐噪声,并且对高斯噪声也有很好的抑制作用;同时,客观评价标准也证明,该算法明显优于传统方法。

Digital image in the process of capture and transmission may be inevitable mixed with some noise, such as salt ＆ pepper noise or Gaussian noise. These noise may have a negative impact on the results of image processing, so we should smooth the image before image processing. The algorithm proposed in this article first captures images of the same scene several times, then takes the median gray of these images in the same position as the gray of the filter image. In order to verify the effectiveness of the algorithm, the article conducted a number of experiments and compared with traditional algo- rithnls, the results show that this algorithm can not only filer out the greatest degree of salt ＆ pepper noise but also has a good inhibiting effect on Gauss noise. Objective assessment criteria also proved that, this algorithm is obviously superior to the traditional method.