Images are often affected by different noise interference in the transmission process. The noise cause wrong information in image analysis. To reduce noise, the simple and easy method is that receiving a few images once time and averages those images to get an average image. But, this method casts huge time cost. If it is difficult to obtain the image, the method is more infeasible. The median filter has better performance for impulse noise and the average filter has good results for lower Gaussian noise. This paper presents a method based on median filter to filter extreme value and designs an adaptive mask according to the number of extreme value in the mask. Then, calculating the similarity for each pixel in the mask and giving weights to pixels in the mask by the principle of proportionality. To do so, the present method can achieve the goal which is removing high-intensity impulse noise and reducing mixed noised interference.
展开▼