BUILT-IN MATHEMATICA SYMBOL

GaussianFilter

filters image by convolving with a Gaussian kernel of pixel radius r.

GaussianFilter

convolves image with a kernel formed from the

derivatives of the discrete Gaussian.

GaussianFilter[image, {r,

}, ...]
uses a Gaussian kernel with radius

and standard deviation

.

GaussianFilter

uses radii

etc. in vertical and horizontal directions.

GaussianFilter

applies Gaussian filtering to an array of data.

MORE INFORMATION

GaussianFilter is a linear smoothing filter commonly used in image processing applications.

GaussianFilter works with arbitrary grayscale or multichannel images, operating separately on each channel.

GaussianFilter is equivalent to GaussianFilter.

GaussianFilter by default gives a real image of the same dimensions as image.

GaussianFilter computes the Gaussian derivative of the vertical dimension in image and the horizontal derivative.

GaussianFilter can take the following options:

Method	"Bessel"	how to determine elements of the Gaussian matrix
Padding	"Fixed"	padding method
WorkingPrecision	Automatic	the precision to use
"Standardization"	True	whether to rescale and shift the Gaussian matrix to account for truncation

Possible settings for the Method option are and .

With a setting Padding->None, GaussianFilter normally gives an image smaller than image.

In GaussianFilter, data can be an array of any rank, and can contain symbolic as well as numerical entries.

EXAMPLES

CLOSE ALL

Basic Examples (5)

Gaussian filter of a 3-channel image, using a 4-pixel radius:

Apply an elliptic Gaussian to blur more in the horizontal direction:

Vertical Gaussian derivative:

Horizontal Gaussian derivative:

Horizontal and vertical derivatives combined:

Apply a Gaussian filter to a list of values:

Gaussian filter of a 3-channel image, using a 4-pixel radius:

In[1]:=

Out[1]=

Apply an elliptic Gaussian to blur more in the horizontal direction:

In[1]:=

Out[1]=

Vertical Gaussian derivative:

In[1]:=

Out[1]=

Horizontal Gaussian derivative:

In[2]:=

In[3]:=

Horizontal and vertical derivatives combined:

In[1]:=

Out[1]=

Apply a Gaussian filter to a list of values:

In[1]:=

Out[1]=

Applications (1)

Compute an unsharp mask:

Add the unsharp mask to the original image:

Properties & Relations (1)

When GaussianFilter is applied to multidimensional data, an explicit convolution range can be specified for each dimension:

This blurs the color channel data only:

Possible Issues (1)

Gaussian filtering of a binary image gives a grayscale image: