Sitelet https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html

WOLFRAM

Wolfram Language & System Documentation Center

ImageCorrespondingPoints[image1,image2]

finds a set of matching interest points in image1 and image2 and returns their pixel coordinates.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Options  
KeypointStrength  
Masking  
MaxFeatures  
Method  
TransformationClass  
Applications  
Properties & Relations  
Neat Examples  
See Also
Related Guides
History
Cite this Page

ImageCorrespondingPoints

ImageCorrespondingPoints[image1,image2]

finds a set of matching interest points in image1 and image2 and returns their pixel coordinates.

Details and Options

  • ImageCorrespondingPoints uses ImageKeypoints to find candidate corresponding points.
  • ImageCorrespondingPoints[image1,image2] returns an expression of the form {points1,points2}, where the pointsi are lists of pixel coordinates representing the matching points in imagei.
  • The following options can be specified:
  • KeypointStrength Automaticminimum strength of the keypoints
    Masking Allregion of interest
    MaxFeatures Automaticmaximum number of keypoints
    Method Automaticthe type of keypoint to use
    TransformationClass Nonegeometrical relation between points
  • With the setting Masking->roi, the set of points is restricted so that the returned points points1 of image1 all lie within the region of interest.
  • With the setting MaxFeatures->n, at most n corresponding points with largest average keypoint strength are returned.
  • By default, a suitable keypoint type is used to find corresponding points. Using Methodmethod, a specific keypoint type or a list of types can be specified.
  • Possible settings for method include:
  • "AKAZE"Accelerated KAZE and binary descriptors
    "BRISK"Binary Robust Invariant Scalable Keypoints
    "KAZE"nonlinear scale-space detector and descriptor
    "ORB"FAST detector and Binary Robust Independent Elementary Features (BRIEF) descriptor
    "SIFT"Scale-Invariant Feature Transform detector and descriptor
    "RootSIFT"SIFT keypoints with an improved descriptor
    "SURF"Speeded-Up Robust Features
    {method1,method2,…}combination of various keypoint correspondences
  • Possible settings for TransformationClass include:
  • Noneno geometric constraints
    "Translation"translation only
    "Rigid"translation and rotation
    "Similarity"translation, rotation, and scaling
    "Affine"linear transformation and translation
    "Perspective"linear fractional transformation
    "Epipolar"epipolar transformation, mapping a point in one image to a line in the other image

Examples

open all close all

Basic Examples  (1)

Corresponding points of two different images of the same object:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Scope  (3)

Corresponding points in binary images:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Corresponding points in grayscale images:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Corresponding points in color images:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Options  (16)

KeypointStrength  (3)

By default, all keypoints are used in finding corresponding points:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Use only keypoints with individual strength greater or equal to a given threshold:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], KeypointStrength -> .001]

Increasing the threshold typically results in detecting fewer corresponding points:

Wolfram Language code: {i1, i2} = {[image], [image]};
Wolfram Language code: ListLinePlot[Table[{s, Length[ImageCorrespondingPoints[i1, i2, KeypointStrength -> s][[1]]]}, {s, .0001, .005, .0001}], Frame -> True, FrameLabel -> {"threshold", "number of corresponding points"}]

Masking  (1)

By default, with Masking->All, all detected corresponding points are returned:

Wolfram Language code: {i1, i2} = {[image], [image]};
Wolfram Language code: MapThread[HighlightImage[#1, #2]&, {{i1, i2}, ImageCorrespondingPoints[i1, i2]}]

With Masking->maskimage, corresponding points of image1 should lie within maskimage:

Wolfram Language code: mask = [image]; c = ImageCorrespondingPoints[i1, i2, Masking -> mask];

Display the detected correspondences for the first image:

Wolfram Language code: HighlightImage[i1, {c[[1]], Orange, mask}]

MaxFeatures  (2)

Return the best correspondences:

Wolfram Language code: c = ImageCorrespondingPoints[[image], [image], MaxFeatures -> 5]

The number of returned correspondences may be less than the value of the MaxFeatures option:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], KeypointStrength -> .001, MaxFeatures -> 5]//First//Length

Method  (3)

By default, "SURF" keypoints are used to find correspondences:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]

Use "KAZE" keypoints:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], Method -> "KAZE"]

Use a combination of "SURF" and "BRISK" keypoints:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], Method -> {"SURF", "BRISK"}]//Short

TransformationClass  (7)

By default, the two detected point sets are not constrained geometrically:

Wolfram Language code: ImageCorrespondingPoints[[image], [image]]//First//Length

Constrain the pair of point sets to be related by an epipolar transformation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Epipolar"]//First//Length

Constrain the pair of point sets to be related by a linear fractional transformation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Perspective"]//First//Length

Constrain the pair of point sets to be related by an affine transformation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Affine"]//First//Length

Constrain the pair of point sets to be related by a similarity transformation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Similarity"]//First//Length

Constrain the pair of point sets to be related by a rigid transformation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Rigid"]//First//Length

Constrain the pair of point sets to be related by a translation:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Translation"]

Applications  (3)

Find matching positions for stereovision applications:

Wolfram Language code: ImageCorrespondingPoints[[image], [image], TransformationClass -> "Perspective"]

Extract the matching patches from two images:

Wolfram Language code: i1 = [image];i2 = [image]; matches = ImageCorrespondingPoints[i1, i2, "Transformation" -> "Perspective"]; MapThread[ImageTrim, {{i1, i2}, matches}]

Find the rotation angle between two images:

Wolfram Language code: i1 = [image];i2 = [image]; matches = ImageCorrespondingPoints[i1, i2]; a1 = ArcTan@@@(# - 1 / 2 * ImageDimensions@i1& /@ matches[[1]]); a2 = ArcTan@@@(# - 1 / 2 * ImageDimensions@i2& /@ matches[[2]]); RootMeanSquare[Mod[a1 - a2, 2 Pi]] / Degree

Properties & Relations  (1)

ImageCorrespondingPoints converts all images to grayscale:

Wolfram Language code: {i1, i2} = {[image], [image]};
Wolfram Language code: ImageCorrespondingPoints[i1, i2] == ImageCorrespondingPoints[Sequence@@ColorConvert[{i1, i2}, "Grayscale"]]

Neat Examples  (1)

Find and visualize matching points in two images of the Moon:

Wolfram Language code: images = { [image], [image]}; matches = ImageCorrespondingPoints@@images; MapThread[Show[#1, Graphics[{Yellow, MapIndexed[Inset[#2[[1]], #1]& , #2]}]]&, {images, matches}]
Wolfram Research (2010), ImageCorrespondingPoints, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html (updated 2021).

Text

Wolfram Research (2010), ImageCorrespondingPoints, Wolfram Language function, https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html (updated 2021).

CMS

Wolfram Language. 2010. "ImageCorrespondingPoints." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2021. https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html.

APA

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

BibTeX

@misc{reference.wolfram_2026_imagecorrespondingpoints, author="Wolfram Research", title="{ImageCorrespondingPoints}", year="2021", howpublished="\url{https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html}", note=[Accessed: 05-October-2026]}

BibLaTeX

@online{reference.wolfram_2026_imagecorrespondingpoints, organization={Wolfram Research}, title={ImageCorrespondingPoints}, year={2021}, url={https://reference.wolfram.com/language/ref/ImageCorrespondingPoints.html}, note=[Accessed: 05-October-2026]}