Non-Local Means Filter
The Non-Local Means Filter is a very powerful tool for reducing noise while keeping edges sharp. Click here to learn more about the underlying theory.
Patch Radius controls the size of the image regions (patches) that are compared during filtering. Larger patches capture more structural information but may smooth fine details.
Search Window Radius defines the neighborhood around each voxel in which similar patches are searched. Increasing this value allows the filter to consider more candidate regions, which can improve denoising at the cost of longer processing times.
Filter Strength determines the amount of smoothing applied. Higher values produce stronger noise reduction but may also blur image details.
For highly noisy images, Enable Prefilter can improve the quality of the patch comparison. In this mode, a Gaussian filter is first applied to reduce noise before the Non-Local Means Filter is executed. This often leads to more reliable similarity estimates and improved denoising performance.
|
Know how! The Non-Local Means Filter can significantly improve the quality of segmentations. However, applying it to a complete dataset may take longer than the application of other filters. Therefore, we recommend to always use the Preview function before to identify the ideal settings. |
The left image shows the original gray values of an image. The right image shows the same image after applying the Non-Local Means Filter using default settings.
|
Know how! You can Save your current settings for this tool as Start-Up Settings . The next time you process an image, these settings will be automatically loaded and filled into the parameter fields. You can also load the Built-In Default Settings available in GeoDict. If you change any settings and want to revert to your saved start-up settings, click the corresponding button to Load the Start-Up Settings . |
