MeanSquares

Mean square error metric configuration

Description

A MeanSquares object describes a mean square error metric configuration that you pass to the function imregister to solve image registration problems.

Creation

You can create a MeanSquares object using the following methods:

• imregconfig — Returns a MeanSquares object paired with an appropriate optimizer for registering monomodal images

• Entering

  metric = registration.metric.MeanSquares;

  on the command line creates a MeanSquares object

Examples

Register Images with Mean Squares Metric

Create a MeanSquares object and use it to register two images with similar brightness and contrast.

Read the reference image and create an unregistered copy.

fixed  = imread('pout.tif');
moving = imrotate(fixed, 5, 'bilinear', 'crop');

View the misaligned images.

figure
imshowpair(fixed, moving,'Scaling','joint');

Create the metric configuration object suitable for registering monomodal images.

metric = registration.metric.MeanSquares

metric = 
  registration.metric.MeanSquares

  This class has no properties.

Create the optimizer configuration object.

optimizer = registration.optimizer.RegularStepGradientDescent;

Modify the metric configuration to get more precision.

optimizer.MaximumIterations = 300;
optimizer.MinimumStepLength = 5e-4;

Perform the registration.

movingRegistered = imregister(moving,fixed,'rigid',optimizer,metric);

View the registered images.

figure
imshowpair(fixed, movingRegistered,'Scaling','joint');

Tips

• The mean squares metric is an element-wise difference between two input images. The ideal value is zero. You can examine the computed values of mean square error if you enable 'DisplayOptimization' when you call imregister. For example, movingRegistered = imregister(moving,fixed,'rigid',optimizer,metric,'DisplayOptimization',true);

Algorithms

The mean squares image similarity metric is computed by squaring the difference of corresponding pixels in each image and taking the mean of the squared differences.