BUILT-IN MATHEMATICA SYMBOL

# MeanShiftFilter

MeanShiftFilter[image, r, d]
replaces each pixel with the mean of the pixels in a range-r neighborhood and whose value is within a distance d.

MeanShiftFilter[array, r, d]
applies mean-shift filtering to a data array.

## Details and OptionsDetails and Options

• MeanShiftFilter[image, r, d] finds the mean of the pixels in × blocks centered on each pixel, taking into account only those pixels whose value is within a Euclidean distance d from the center pixel.
• At the edges of an image, MeanShiftFilter uses smaller neighborhoods.
• MeanShiftFilter works with 3D as well as 2D images, and also with data arrays of any rank.
• MeanShiftFilter[image, {rrow, rcol}, d] uses range in height, and in width.
• MeanShiftFilter[image, {rslice, rrow, rcol}, d] uses range in height, in depth, and in width.
• MeanShiftFilter works with binary, grayscale, RGB, and arbitrary multichannel images.
• With a setting , at most n iterations will be performed.
• MeanShiftFilter accepts a DistanceFunction option, which can be used to specify how the distance between pixel values is computed. The default setting is .
• For a complete list of possible settings for DistanceFunction, see the reference page for MeanShift.
• The possible range for the distance parameter d depends on the distance function used as well as the dimension of the color space.

## ExamplesExamplesopen allclose all

### Basic Examples (2)Basic Examples (2)

Mean-shift filtering of a color image:

 Out[1]=

Mean-shift filtering of a grayscale image:

 Out[1]=