ITK/Examples/Metrics/MeanSquaresImageToImageMetric

Image to image metrics are typically used for image registration. However, they can be used independent of registration to compute the metric between two images. The set-up to compute the metric is a bit complex, since the set-up is normally done by the registration method. This example computes the mean squares difference between two images. 25 samples are taken, translating the second image over the first image. If the two images specify the same image, the example illustrates how the metric varies over the samples. In this case, the metric at (0,0) should be 0.

MeanSquaresImageToImageMetric.cxx

<source lang="cpp">

1. include "itkImage.h"
2. include "itkImageFileReader.h"
3. include "itkMeanSquaresImageToImageMetric.h"
4. include "itkLinearInterpolateImageFunction.h"
5. include "itkTranslationTransform.h"

int main(int argc, char *argv[]) {

typedef itk::Image< double, 2 >         ImageType;
typedef itk::ImageFileReader<ImageType> ReaderType;

if (argc < 3)
  {
  std::cout << "Usage: " << argv[0] << " imageFile1 imageFile2" << std::endl;
  return EXIT_FAILURE;
  }
ReaderType::Pointer fixedReader = ReaderType::New();
fixedReader->SetFileName(argv[1]);
fixedReader->Update();

ReaderType::Pointer movingReader = ReaderType::New();
movingReader->SetFileName(argv[2]);
movingReader->Update();

ImageType::Pointer fixedImage = fixedReader->GetOutput();
ImageType::Pointer movingImage = movingReader->GetOutput();

typedef itk::MeanSquaresImageToImageMetric < ImageType , ImageType > 
                                               MetricType;
typedef itk::LinearInterpolateImageFunction<ImageType, double >
                                               InterpolatorType;
typedef itk::TranslationTransform < double , 2 > TransformType;

MetricType::Pointer metric = MetricType::New();
TransformType::Pointer transform = TransformType::New();

InterpolatorType::Pointer interpolator = InterpolatorType::New();
interpolator->SetInputImage( fixedImage );

metric->SetFixedImage( fixedImage );
metric->SetMovingImage( movingImage );
metric->SetFixedImageRegion( fixedImage->GetLargestPossibleRegion() );
metric->SetTransform( transform );
metric->SetInterpolator( interpolator );

TransformType::ParametersType params(transform->GetNumberOfParameters());
params.Fill(0.0);

metric->Initialize();
for (double x = -10.0; x <= 10.0; x+=5.0)
  {
  params(0) = x;
  for (double y = -10.0; y <= 10.0; y+=5.0)
    {
    params(1) = y;
    std::cout << params << ": " << metric->GetValue( params ) << std::endl ;
    }
  }

return EXIT_SUCCESS;

} </source>

CMakeLists.txt

<syntaxhighlight lang="cmake"> cmake_minimum_required(VERSION 3.9.5)

project(MeanSquaresImageToImageMetric)

find_package(ITK REQUIRED) include(${ITK_USE_FILE}) if (ITKVtkGlue_LOADED)

 find_package(VTK REQUIRED)
 include(${VTK_USE_FILE})

endif()

add_executable(MeanSquaresImageToImageMetric MACOSX_BUNDLE MeanSquaresImageToImageMetric.cxx)

if( "${ITK_VERSION_MAJOR}" LESS 4 )

 target_link_libraries(MeanSquaresImageToImageMetric ITKReview ${ITK_LIBRARIES})

else( "${ITK_VERSION_MAJOR}" LESS 4 )

 target_link_libraries(MeanSquaresImageToImageMetric ${ITK_LIBRARIES})

endif( "${ITK_VERSION_MAJOR}" LESS 4 )

</syntaxhighlight>

Download and Build MeanSquaresImageToImageMetric

Click here to download MeanSquaresImageToImageMetric and its CMakeLists.txt file. Once the tarball MeanSquaresImageToImageMetric.tar has been downloaded and extracted,

cd MeanSquaresImageToImageMetric/build

• If ITK is installed:

cmake ..

• If ITK is not installed but compiled on your system, you will need to specify the path to your ITK build:

cmake -DITK_DIR:PATH=/home/me/itk_build ..

Build the project:

make

and run it:

./MeanSquaresImageToImageMetric

WINDOWS USERS PLEASE NOTE: Be sure to add the ITK bin directory to your path. This will resolve the ITK dll's at run time.

Building All of the Examples

Many of the examples in the ITK Wiki Examples Collection require VTK. You can build all of the the examples by following these instructions. If you are a new VTK user, you may want to try the Superbuild which will build a proper ITK and VTK.

ItkVtkGlue

ITK >= 4

For examples that use QuickView (which depends on VTK), you must have built ITK with Module_ITKVtkGlue=ON.

ITK < 4

Some of the ITK Examples require VTK to display the images. If you download the entire ITK Wiki Examples Collection, the ItkVtkGlue directory will be included and configured. If you wish to just build a few examples, then you will need to download ItkVtkGlue and build it. When you run cmake it will ask you to specify the location of the ItkVtkGlue binary directory.