WOLFRAM

Wolfram Language & System Documentation Center

CornerFilter[image]

computes a measure for the presence of a corner for each pixel in image and returns the result as an intensity image.

CornerFilter[image,r]

detects corners at a pixel range r.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Data  
Parameters  
Options  
Method  
Applications  
Properties & Relations  
See Also
Related Guides
History
Cite this Page

CornerFilter

CornerFilter[image]

computes a measure for the presence of a corner for each pixel in image and returns the result as an intensity image.

CornerFilter[image,r]

detects corners at a pixel range r.

Details and Options

  • CornerFilter implements a variety of corner-detection methods based on gradient computations.
  • CornerFilter works with arbitrary 2D and 3D images.
  • When applied to multichannel images, CornerFilter finds corner signatures across channels.
  • CornerFilter[image] is equivalent to CornerFilter[image,2].
  • CornerFilter[image,{r1,r2}] specifies different radii in vertical and horizontal directions.
  • CornerFilter takes a Method option that specifies how to compute the corner metric. The default setting is "ShiTomasi". Available methods include:
  • "HarmonicMean"harmonic mean of eigenvalues method
    "HarrisStephens"Harris–Stephens corner detection
    {"HarrisStephens",k}Harris–Stephens method with sensitivity parameter k
    "ShiTomasi"minimum eigenvalue method
  • By default, the Harris–Stephens method uses a sensitivity parameter with Image objects and with Image3D objects.
  • The parameters of the Gaussian derivatives to be computed can be specified using Method->{method,"Gaussian"->{ρ,σ}}. The default setting is "Gaussian"->{r,r/2}.

Examples

open all close all

Basic Examples  (2)

Find corners in an image:

Wolfram Language code: CornerFilter[[image]]//ImageAdjust

Detect corners in a 3D image:

Wolfram Language code: CornerFilter[[image]]//ImageAdjust

Scope  (5)

Data  (2)

Detect a corner in a binary image:

Wolfram Language code: CornerFilter[[image]] // ImageAdjust

Detect corners in a multichannel image:

Wolfram Language code: CornerFilter[[image], 5]//ImageAdjust

Parameters  (3)

Detect corners at a small scale:

Wolfram Language code: CornerFilter[[image], 1] // ImageAdjust

Corners at a larger scale:

Wolfram Language code: CornerFilter[[image], 5] // ImageAdjust

Use a rectangular pixel range:

Wolfram Language code: CornerFilter[[image], {8, 4}]//ImageAdjust

Detect corners in a 3D image at a low pixel range:

Wolfram Language code: volume = ImageResize[ExampleData[{"TestImage3D", "CThead"}], {100, 100, 100}]
Wolfram Language code: CornerFilter[volume, 1]//ImageAdjust

Increase the range of the corner detector:

Wolfram Language code: CornerFilter[volume, 5]//ImageAdjust

Options  (2)

Method  (2)

Wolfram Language code: i = [image];

Detect corners using the default method:

Wolfram Language code: CornerFilter[i]//ImageAdjust

Use the "HarmonicMean" method:

Wolfram Language code: CornerFilter[i, Method -> "HarmonicMean"]//ImageAdjust

Detect corners using the Harris–Stephens method, which gives a negative signature for edges:

Wolfram Language code: CornerFilter[i, Method -> "HarrisStephens"]//ImageAdjust

Specify Gaussian derivative parameters:

Wolfram Language code: ImageAdjust[CornerFilter[[image], 5, Method -> {"ShiTomasi", "Gaussian" -> {#, # / 2}}]]& /@ {1, 10}

Applications  (2)

Find corners in text:

Wolfram Language code: i = [image]; c = CornerFilter[i] //ImageAdjust

Highlight the detected corners:

Wolfram Language code: HighlightImage[i, Binarize[c, 0.6]]

Use a CornerFilter to highlight small stars on an astronomical image:

Wolfram Language code: i = [image]; ii = CornerFilter[i, .7]//ImageAdjust; i + 1.5ii

Properties & Relations  (1)

ImageCorners are peaks of the CornerFilter using non-max suppression:

Wolfram Language code: i = [image]; cf = CornerFilter[i, 2]; cf//ImageAdjust

Apply non-max suppression and visualize detected corners:

Wolfram Language code: nonmaxSuppression[img_] := Binarize[ImageSubtract[MaxFilter[img, 1], img], {0, 0}];
Wolfram Language code: corners = ImageMultiply[nonmaxSuppression[cf], Binarize[cf, .009]]
Wolfram Language code: HighlightImage[i, Dilation[corners, 1]]

Compare with the result of ImageCorners:

Wolfram Language code: HighlightImage[i, ImageCorners[i, 2, .009]]

Use MaxDetect for finding the peaks:

Wolfram Language code: md = MaxDetect[cf, .009]
Wolfram Language code: HighlightImage[i, ComponentMeasurements[md, "Centroid"][[All, 2]]]
Wolfram Research (2010), CornerFilter, Wolfram Language function, https://reference.wolfram.com/language/ref/CornerFilter.html (updated 2014).

Text

Wolfram Research (2010), CornerFilter, Wolfram Language function, https://reference.wolfram.com/language/ref/CornerFilter.html (updated 2014).

CMS

Wolfram Language. 2010. "CornerFilter." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2014. https://reference.wolfram.com/language/ref/CornerFilter.html.

APA

Wolfram Language. (2010). CornerFilter. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/CornerFilter.html

BibTeX

@misc{reference.wolfram_2026_cornerfilter, author="Wolfram Research", title="{CornerFilter}", year="2014", howpublished="\url{https://reference.wolfram.com/language/ref/CornerFilter.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_cornerfilter, organization={Wolfram Research}, title={CornerFilter}, year={2014}, url={https://reference.wolfram.com/language/ref/CornerFilter.html}, note=[Accessed: 13-June-2026]}