Filtering is a basic operation in image processing and computer vision. Gaussian low-pass filtering is the most commonly used, and its principle is weighted average of neighborhood pixels value. This average among neighbours will have some fuzzy border and the image is blurred. Bilateral filtering has raised to address the problem of blurring edges. Not only does it take into account spatial proximity also considers the similarity of brightness. Only the neighborhood of similar intensity is averaged. Bilateral filtering have a great deal of improvement and development both in theory and applications.Based on the bilateral filter, the main works of this paper are as follow:(1) Through the experiment, we have summed a criterion of selecting parameter for bilateral filter.(2) Combing median filter and bilateral filter together, pseudo-median bilateral filter has been proposed, which increases the performance of removing salt-pepper noise.(3) A new edge detection has been proposed based on bilateral filter and non-local means. |