WOLFRAM

Wolfram Language & System Documentation Center

CommonestFilter[data,r]

filters data by replacing every value with the most common value in its range-r neighborhood.

CommonestFilter[data,{r1,r2,…}]

uses ri for filtering the ^(th)dimension in data.

Details
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Data  
Parameters  
Applications  
Properties & Relations  
Possible Issues  
Neat Examples  
See Also
Tech Notes
Related Guides
History
Cite this Page

CommonestFilter

CommonestFilter[data,r]

filters data by replacing every value with the most common value in its range-r neighborhood.

CommonestFilter[data,{r1,r2,…}]

uses ri for filtering the ^(th)dimension in data.

Details

  • CommonestFilter, also known as majority filter, is used to filter data by returning the commonest local value, where the extent of the effect is dependent on the value of r.
  • The function applied to each range-r neighborhood is Commonest.
  • If more than one commonest pixel exists and the center pixel is one of them, the center pixel is used. Otherwise, the pixel is replaced with a random commonest.
  • The data can be any of the following:
  • listarbitrary-rank numerical array
    tseriestemporal data such as TimeSeries, TemporalData, …
    imagearbitrary Image or Image3D object
    audioan Audio object
    videoa Video object
  • For multichannel images, CommonestFilter replaces each pixel by the commonest pixel vector in the neighborhood.
  • CommonestFilter[data,{r1,r2,…}] computes the commonest value in blocks centered on each sample.
  • CommonestFilter assumes the index coordinate system for lists and images.
  • At the data boundaries, CommonestFilter uses smaller neighborhoods.

Examples

open all close all

Basic Examples  (3)

Apply a majority filter to a vector of numbers:

Wolfram Language code: CommonestFilter[{0, 1, -1, 1, 2, 1, 3, 3, 3, 1}, 1]

Filter a TimeSeries:

Wolfram Language code: ts = TemporalData[TimeSeries, {{{-1, -2, -4, -4, -6, -7, -8, -11, -13, -11, -12, -11, -11, -12, -13, -13, -12, -11, -9, -8, -8, -7, -6, -7, -10, -11, -10, -9, -10, -9, -7, -7, -7, -8, -7, -7, -7, -8, -7, -8, -8, -7, -7, -7, -6, -6, -6, -7, -7, ... 2, -73, -73, -73, -74, -73, -73, -74, -75, -76, -75, -75, -74, -73, -72, -73, -75, -74, -74, -74}}, {{0, 782, 1}}, 1, {"Continuous", 1}, {"Discrete", 1}, 1, {ResamplingMethod -> {"Interpolation", InterpolationOrder -> 1}}}, False, 11.1];
Wolfram Language code: filtered = CommonestFilter[ts, 50]
Wolfram Language code: ListLinePlot[{ts, filtered}, PlotLegends -> {"original data", "filtered"}]

Commonest filtering of a color image:

Wolfram Language code: CommonestFilter[[image], 3]

Scope  (12)

Data  (8)

Commonest filtering applied to arbitrary expressions:

Wolfram Language code: CommonestFilter[ {a, b, b, c, c, c, d, d, e}, 2]

Majority filtering of a 2D array:

Wolfram Language code: CommonestFilter[(⁠| | | | | | - | - | - | - | | 1 | 1 | 2 | 0 | | 2 | 3 | 1 | 1 | | 1 | 1 | 0 | 0 | | 0 | 1 | 2 | 3 |⁠), 1]//MatrixForm

Filter a quantity array:

Wolfram Language code: data = {Quantity[2, "Meters"], Quantity[0, "Meters"], Quantity[0, "Meters"], Quantity[3, "Meters"], Quantity[0, "Meters"], Quantity[1, "Meters"], Quantity[3, "Meters"], Quantity[1, "Meters"], Quantity[1, "Meters"], Quantity[3, "Meters"], Quantity[3, "Meters"], Quantity[1, "Meters"]};
Wolfram Language code: filtered = CommonestFilter[data, 1]

Filter an EventSeries:

Wolfram Language code: es = TemporalData[EventSeries, {{{8, 3, 1, 4, 10, 9, 4, 8, 5, 3, 5, 6, 1, 8, 3, 3, 2, 5, 0, 6, 4, 4, 3, 10, 0, 1, 1, 10, 3, 5, 2, 1, 8, 8, 2, 10, 9, 5, 4, 9, 8, 5, 1, 2, 8, 10, 0, 5, 8, 10, 0, 4, 4, 5, 8, 0, 8, 2, 3, 5, 9, 6, 5, 6, 10, 1, 8, 4 ... , 4, 0, 0, 7, 4, 6, 6, 6, 7, 7, 1, 9, 2, 3, 9, 10, 6, 2, 9, 7, 10, 5, 9, 7, 7, 9, 6, 7, 8, 6, 7, 8, 0, 2, 5, 5, 8, 7, 0, 9, 2, 2, 4, 5}}, {{0, 149, 1}}, 1, {"Discrete", 1}, {"Discrete", 1}, 1, {ResamplingMethod -> None}}, False, 10.1];
Wolfram Language code: filtered = CommonestFilter[es, 10]
Wolfram Language code: ListPlot[{es, filtered}, PlotLegends -> {"original data", "filtered"}, Filling -> Axis]

Filter an Audio signal:

Wolfram Language code: a = Import["ExampleData/rule30.wav"];
Wolfram Language code: b = CommonestFilter[a, 35]
Wolfram Language code: AudioPlot[{a, b}]

Filtering a 2D grayscale image:

Wolfram Language code: CommonestFilter[[image], 5]

Filter video frames:

Wolfram Language code: CommonestFilter[Video["ExampleData/fish.mp4"], 3]

Apply commonest filtering to a 3D volume:

Wolfram Language code: CommonestFilter[ExampleData[{"TestImage3D", "CTengine"}], 2]

Parameters  (4)

Specify one radius to be used in all directions:

Wolfram Language code: CommonestFilter[[image], 3]

Increasing the radius will increase the regions of uniform value in images:

Wolfram Language code: Table[Labeled[CommonestFilter[[image], r], Text["*r* = " <> ToString@r]], {r, {1, 3, 6}}]

Majority filtering just in the first direction:

Wolfram Language code: CommonestFilter[[image], {10, 0}]

Second direction:

Wolfram Language code: CommonestFilter[[image], {0, 10}]

Commonest filtering of a 3D image in the vertical direction only:

Wolfram Language code: CommonestFilter[[image], {15, 0, 0}]

Filtering of the horizontal planes only:

Wolfram Language code: CommonestFilter[[image], {0, 5, 5}]

Applications  (2)

Replacing each pixel with the most common color in its neighborhood creates a posterization effect:

Wolfram Language code: CommonestFilter[[image], 5]

Majority filtering removes noise from a binary image:

Wolfram Language code: CommonestFilter[[image], 1]

Properties & Relations  (1)

Commonest filter gives the same result as MedianFilter on binary images:

Wolfram Language code: i = [image]; CommonestFilter[i, 3] === MedianFilter[i, 3]

Possible Issues  (1)

Majority filtering may not have the desired effect when applied to real-valued data, since all sample values may be unique:

Wolfram Language code: x = RandomReal[{0, 3}, 8]
Wolfram Language code: CommonestFilter[x, 1]

Quantize the sample values to overcome this problem:

Wolfram Language code: CommonestFilter[Floor[x], 1]//N

Neat Examples  (1)

Commonest filtering applied to random noise:

Wolfram Language code: CommonestFilter[Image[RandomImage[], "Byte"], 20]
Wolfram Research (2008), CommonestFilter, Wolfram Language function, https://reference.wolfram.com/language/ref/CommonestFilter.html (updated 2025).

Text

Wolfram Research (2008), CommonestFilter, Wolfram Language function, https://reference.wolfram.com/language/ref/CommonestFilter.html (updated 2025).

CMS

Wolfram Language. 2008. "CommonestFilter." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/CommonestFilter.html.

APA

Wolfram Language. (2008). CommonestFilter. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/CommonestFilter.html

BibTeX

@misc{reference.wolfram_2026_commonestfilter, author="Wolfram Research", title="{CommonestFilter}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/CommonestFilter.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_commonestfilter, organization={Wolfram Research}, title={CommonestFilter}, year={2025}, url={https://reference.wolfram.com/language/ref/CommonestFilter.html}, note=[Accessed: 13-June-2026]}