smooth3

Smooth 3-D data

Syntax

W = smooth3(V)

W = smooth3(V,method)

W = smooth3(V,method,size)

W = smooth3(V,method,size,sd)

Description

W = smooth3(V) smooths the volumetric data V and returns the smoothed data in W. W is a double array with the same dimensions as V.

W = smooth3(V,method) uses the specified smoothing method to define the convolution kernel and smooth the data.

W = smooth3(V,method,size) specifies the 3-D window size for the smoothing method.

W = smooth3(V,method,size,sd) specifies the standard deviation for the "gaussian" smoothing method.

Examples

Smooth 3-D Data

Load the mri data set and squeeze the 4-D array stored in the D variable into three dimensions. Then smooth the data.

load mri
D = squeeze(D);
W = smooth3(D);

Display the raw data and the smoothed data as an isosurface.

figure
tiledlayout(1,2)
nexttile
p1 = patch(isosurface(D,5),"FaceColor","cyan", ...
    "EdgeColor","none");
view(3)
daspect([1,1,0.4])
camlight
isonormals(D,p1)
title("Raw Data")

nexttile
p2 = patch(isosurface(W,5),"FaceColor","cyan", ...
    "EdgeColor","none");
view(3)
daspect([1,1,0.4])
camlight
isonormals(W,p2)
title("Smoothed Data")

Specify Smoothing Method

Create a 10-by-10-by-10 array of random data. Smooth the data using the "gaussian" method with a 3-D window size of 5.

data = rand(10,10,10);
data = smooth3(data,"gaussian",5);

Display the data as an isosurface with end caps.

patch(isocaps(data,0.5), ...
   "FaceColor","interp","EdgeColor","none")
p1 = patch(isosurface(data,0.5), ...
   "FaceColor","blue","EdgeColor","none");
isonormals(data,p1)
view(3) 
axis vis3d tight
camlight left
lighting gouraud

Input Arguments

V — Volumetric data

3-D array

Volumetric data, specified as a 3-D array.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

method — Smoothing method

"box" (default) | "gaussian"

Smoothing method, specified as one of these filters:

• "box" — Weighted moving average over each window of V

• "gaussian" — Gaussian-weighted moving average over each window of V

The smoothing method determines the convolution kernel.

size — Window size

[3 3 3] (default) | three-element vector of positive odd integers | positive odd integer scalar

Window size of the selected smoothing method, specified as a three-element vector of positive odd integers or a positive odd integer scalar. If size is scalar, then size is interpreted as [size size size].

The window size determines how much smoothing is applied to the data. As the window size increases, more data points are used for the averaging process, and therefore more smoothing occurs.

When using the "gaussian" smoothing method, both standard deviation and window size determine how much smoothing is applied to the data.

sd — Standard deviation

0.65 (default) | numeric value

Standard deviation for the "gaussian" smoothing method, specified as a numeric value. As the standard deviation value increases, more averaging is applied within the filter window.

If the smoothing method is set to "box", sd has no effect.

Data Types: single | double

Extended Capabilities

GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

The smooth3 function supports GPU array input with these usage notes and limitations:

• This function accepts GPU arrays, but does not run on a GPU.

For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

Distributed Arrays

Partition large arrays across the combined memory of your cluster using Parallel Computing Toolbox™.

Usage notes and limitations:

• This function operates on distributed arrays, but executes in the client MATLAB^®.

For more information, see Run MATLAB Functions with Distributed Arrays (Parallel Computing Toolbox).

Version History

Introduced before R2006a