smoothn

SMOOTHN allows automatized and robust smoothing in arbitrary dimension w/wo missing values

http://www.biomecardio.com

Download
Download

You are now following this Submission

Editor's Note: This file was selected as MATLAB Central Pick of the Week

Cite As

Damien Garcia (2026). smoothn (https://uk.mathworks.com/matlabcentral/fileexchange/25634-smoothn), MATLAB Central File Exchange. Retrieved .

Garcia, Damien. “Robust Smoothing of Gridded Data in One and Higher Dimensions with Missing Values.” Computational Statistics & Data Analysis, vol. 54, no. 4, Elsevier BV, Apr. 2010, pp. 1167–78, doi:10.1016/j.csda.2009.09.020.

View more styles

Garcia, Damien. “A Fast All-in-One Method for Automated Post-Processing of PIV Data.” Experiments in Fluids, vol. 50, no. 5, Springer Science and Business Media LLC, Oct. 2010, pp. 1247–59, doi:10.1007/s00348-010-0985-y.

View more styles

General Information

MATLAB Release Compatibility

  • Compatible with R2017a to R2020a

Platform Compatibility

  • Windows
  • macOS
  • Linux
Version Published Release Notes Action
2.3.0

BSXFUN is no longer used (version thus must be >= R2017)

Download
2.2.1

verLessThan('matlab','9.2'); instead of verLessThan('matlab','9.1');

Download
2.2.0

- fixed bug in isstruct(varargin{end-1})
- no longer use BSXFUN w/ recent Matlab versions

Download
2.1.4

updated links

Download
2.1.3

updated links

Download
2.1.2

updated links

Download
2.1.1

.

Download
2.1.0

minor updates: 1) use narginchk, 2) two warning messages slightly modified

Download
2.0.0

minor update: 1) use narginchk, 2) some warning messages slightly modified

Download
1.37.0

I noticed a minor error in one comment

Download
1.36.0

.

Download
1.35.0

.

Download
1.34.0

Some modifications in the help text

Download
1.33.0

To simplify the syntax, the termination parameters are now in a structure (OPTIONS).

Download
1.32.0

Numerical adjustment in the leverage (for robust smoothing) in the case of unequal spacing increments.

Download
1.31.0

SMOOTHN, by default, assumes that the spacing increments are constant and equal in all the directions (i.e. dx = dy = dz = ...). Spacing increments that differ from one direction to the other can now be used (enter "help smoothn" for details).

Download
1.30.0

There was a non negligible bug in the new SMOOTHN function:
d = ndims(y) => d = ndims(y{1})
Many thanks to Gianni Pedrizzetti.

Download
1.28.0

Update of the help text

Download
1.27.0

A minor bug in the "Initial Guess" criterion has been removed

Download
1.26.0

A bug was present when dealing with complex numbers

Download
1.25.0

A small bug was present in the subfunction InitialGuess (Thank you Jonathan!)

Download
1.24.0

One bug has been fixed.

Download
1.23.0

SMOOTHN now works with multicomponent data (e.g. 3D vector fields) by using cell arrays. See the help text for details.

Download
1.22.0

DCTN and IDCTN are now included in SMOOTHN

Download
1.21.0

some typos

Download
1.20.0

3 optional weighting functions

Download
1.19.0

3 optional weighting functions

Download
1.12.0

minor modifications: mlint messages removed

Download
1.11.0

Some options have been removed/added

Download
1.10.0

fix a minor bug with the warning messages

Download
1.9.0

Minor modification in the relaxation factor

Download
1.8.0

A minor bug in error(nargchk(...))

Download
1.7.0

Gamma was undefined when "isauto" variable was false.

Download
1.6.0

The link to the manuscript has been modified.

Download
1.5.0

A bug has been reported with a smoothness parameter input. Thank you B.S.

Download
1.3.0

Very much faster now with weighted/missing data:
1) SOR
2) Initial guess from nearest-neighbor interpolation
3) GCV score is minimized every 2^k iterations (k = 0...)

Download
1.2.0

The "upsample" option has been removed

Download
1.1.0

An example has been added

Download
1.0.0

Download