Intensity-based image registration
transforms the 2-D or 3-D grayscale image,
moving_reg = imregister(
moving, so that it
is registered with the reference image,
transformType defines the type of transformation to
metric defines the quantitative measure of similarity
between the images to optimize.
optimizer describes the method
for optimizing the metric. The function returns the registered image,
transforms the spatially referenced image
moving so that it is
registered with the spatially referenced image
Rfixed are spatial
referencing objects that describe the world coordinate limits and the resolution of
___ = imregister(___,
specifies additional options with one or more name-value pair arguments.
Read two images. This example uses two magnetic resonance (MRI) images of a knee. The fixed image is a spin echo image, while the moving image is a spin echo image with inversion recovery. The two sagittal slices were acquired at the same time but are slightly out of alignment.
fixed = dicomread('knee1.dcm'); moving = dicomread('knee2.dcm');
View the misaligned images.
Create the optimizer and metric, setting the modality to
'multimodal' since the images come from different sensors.
[optimizer, metric] = imregconfig('multimodal')
optimizer = registration.optimizer.OnePlusOneEvolutionary Properties: GrowthFactor: 1.050000e+00 Epsilon: 1.500000e-06 InitialRadius: 6.250000e-03 MaximumIterations: 100
metric = registration.metric.MattesMutualInformation Properties: NumberOfSpatialSamples: 500 NumberOfHistogramBins: 50 UseAllPixels: 1
Tune the properties of the optimizer to get the problem to converge on a global maxima and to allow for more iterations.
optimizer.InitialRadius = 0.009; optimizer.Epsilon = 1.5e-4; optimizer.GrowthFactor = 1.01; optimizer.MaximumIterations = 300;
Perform the registration.
movingRegistered = imregister(moving, fixed, 'affine', optimizer, metric);
View the registered images.
figure imshowpair(fixed, movingRegistered,'Scaling','joint')
moving— Image to be registered
Image to be registered, specified as numeric matrix representing a 2-D grayscale image or a 3-D numeric array representing a 3-D grayscale volume.
fixed— Reference image
Reference image in the target orientation, specified as numeric matrix
representing a 2-D grayscale image or a 3-D numeric array representing a 3-D
grayscale volume. The reference image must have the same dimensionality as
the image to be registered,
transformType— Geometric transformation to be applied to image to be registered
Geometric transformation to be applied to the moving image, specified as one of the following values:
|(x,y) translation in 2-D, or (x,y,z) translation in 3-D.|
|Rigid transformation consisting of translation and rotation.|
|Nonreflective similarity transformation consisting of translation, rotation, and scale.|
|Affine transformation consisting of translation, rotation, scale, and shear.|
transformation types always involve nonreflective transformations.
comma-separated pairs of
the argument name and
Value is the corresponding value.
Name must appear inside quotes. You can specify several name and value
pair arguments in any order as
'DisplayOptimization',1enables the verbose optimization mode.
DisplayOptimization— Verbose optimization flag
Verbose optimization flag, specified as the comma-separated
pair consisting of
'DisplayOptimization', and the
imregister displays optimization
information in the command window during the registration process.
PyramidLevels— Number of pyramid levels used during registration process
3(default) | positive integer
Number of pyramid levels used during the registration process,
specified as the comma-separated pair consisting of
a positive integer.
'PyramidLevels',4 sets the number
of pyramid levels to
moving_reg— Registered image
Registered image, returned as a 2-D numeric matrix representing a 2-D
grayscale image or a 3-D numeric array representing a 3-D grayscale volume.
Any fill pixels introduced that do not correspond to locations in the
original image are
imregister use the same underlying registration
imregister performs the additional step of
moving to produce the registered output image
from the geometric transformation estimate calculated by
you want access to the geometric transformation that relates
imregister when you want a registered output
imregconfig function before
imregister. Getting good results from
optimization-based image registration usually requires modifying optimizer or
metric settings for the pair of images being registered. The
imregconfig function provides a default configuration
that should only be considered a starting point. For example, if you increase
the number of iterations in the optimizer, reduce the optimizer step size, or
change the number of samples in a stochastic metric, the registration improves
to a point, at the expense of performance. See the output of
imregconfig for more information on the different
parameters that you can modify.
If the spatial scaling of your images differs by more than 10%, resize them
imresize before registering them.
You can use
imregister in an
automated workflow to register several images.
When you have spatial referencing information about the image to be
registered, specify the information to
spatial referencing objects. This helps
to better results more quickly because scale differences can be taken into