This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English verison of the page.

Note: This page has been translated by MathWorks. Please click here
To view all translated materals including this page, select Japan from the country navigator on the bottom of this page.


Detect corners using minimum eigenvalue algorithm and return cornerPoints object


  • points = detectMinEigenFeatures(I)
  • points = detectMinEigenFeatures(I,Name,Value)



points = detectMinEigenFeatures(I) returns a cornerPoints object, points. The object contains information about the feature points detected in a 2-D grayscale input image, I. The detectMinEigenFeatures function uses the minimum eigenvalue algorithm developed by Shi and Tomasi to find feature points.

points = detectMinEigenFeatures(I,Name,Value) ) uses additional options specified by one or more Name,Value pair arguments.

Code Generation Support:
Supports Code Generation: Yes
Compile-time constant input: 'FilterSize'
Supports MATLAB Function block: No
Code Generation Support, Usage Notes, and Limitations


collapse all

Read the image.

I = checkerboard;

Find the corners.

corners = detectMinEigenFeatures(I);

Display the results.

imshow(I); hold on;

Related Examples

Input Arguments

collapse all

Input image, specified in 2-D grayscale. The input image must be real and nonsparse.

Data Types: single | double | int16 | uint8 | uint16 | logical

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside single quotes (' '). You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: 'MinQuality','0.01','ROI', [50,150,100,200] specifies that the detector must use a 1% minimum accepted quality of corners within the designated region of interest. This region of interest is located at x=50, y=150. The ROI has a width of 100 pixels, and a height of 200 pixels.

collapse all

Minimum accepted quality of corners, specified as the comma-separated pair consisting of 'MinQuality' and a scalar value in the range [0,1].

The minimum accepted quality of corners represents a fraction of the maximum corner metric value in the image. Larger values can be used to remove erroneous corners.

Example: 'MinQuality', 0.01

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

Gaussian filter dimension, specified as the comma-separated pair consisting of 'FilterSize' and an odd integer value in the range [3, inf).

The Gaussian filter smooths the gradient of the input image.

The function uses the FilterSize value to calculate the filter's dimensions, FilterSize-by-FilterSize. It also defines the standard deviation as FilterSize/3.

Example: 'FilterSize', 5

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

Rectangular region for corner detection, specified as a comma-separated pair consisting of 'ROI' and a vector of the format [x y width height]. The first two integer values [x y] represent the location of the upper-left corner of the region of interest. The last two integer values represent the width and height.

Example: 'ROI', [50,150,100,200]

Output Arguments

collapse all

Corner points, returned as a cornerPoints object. The object contains information about the feature points detected in the 2-D grayscale input image.


[1] Shi, J., and C. Tomasi, "Good Features to Track," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 1994, pp. 593–600.

Introduced in R2013a

Was this topic helpful?