完整WORD文檔請查看http://download.csdn.net/source/2285738
1.什麼叫配準
Image registration is the process of determining the spatial transform that maps points from one image to homologous points on a object in the second image.
2.配準的框架
3．Transform
In the Insight Toolkit, itk::Transform objects encapsulate the mapping of points and vectors from an input space to an output space.
ITK provides a variety of transforms from simple translation, rotation and scaling to general affine and kernel transforms.
下面詳細介紹一些主要的變換方法：
3.1 Translation Transform
3.2 Scale Transform
3.3 Euler2DTransform
3.4 CenteredRigid2DTransform
3.5 Similarity2DTransform
can be seen as a rigid transform combined with an isotropic scaling factor.
3.6 AffineTransform
3.7 變換的分類
4. Interpolators
4.1 爲什麼要插值?
4.2 最常用的兩種插值方法
4.2.1 Nearest Neighbor Interpolation
4.2.2 Linear Interpolation
5. Metrics
In ITK, itk::ImageToImageMetric objects quantitatively measure how well the transformed moving image fits the fixed image by comparing the gray-scale intensity of the images. These metrics are very flexible and can work with any transform or interpolation method and do not require reduction of the gray-scale images to sparse extracted information such as edges.
下面介紹一些常用的Metrics
5.1 Mean Squares Metric
The itk::MeanSquaresImageToImageMetric computes the mean squared pixel-wise difference in intensity between image A and B over a user defined region
5.2 Normalized Correlation Metric
6. Optimizers
The basic input to an optimizer is a cost function object
常用的兩種方法
6.1 Gradient Descent
Advances parameters in the direction of the gradient where the step size is governed by a learning rate ( itk::GradientDescentOptimizer).
6.2 Regular Step Gradient Descent
Advances parameters in the direction of the gradient where a bipartition scheme is used to compute the step size (itk::RegularStepGradientDescentOptimizer).
7.一個簡單的例子
實現平移配準
|
#include "itkImageRegistrationMethod.h" #include "itkTranslationTransform.h" #include "itkLinearInterpolateImageFunction.h" #include "itkMeanSquaresImageToImageMetric.h" #include "itkRegularStepGradientDescentOptimizer.h" #include "itkImage.h"
#include "itkImageFileReader.h" #include "itkImageFileWriter.h"
#include "itkResampleImageFilter.h"
#include "itkCommand.h"
class CommandIterationUpdate : public itk::Command { public: typedef CommandIterationUpdate Self; typedef itk::Command Superclass;
typedef itk::SmartPointer<Self> Pointer;
itkNewMacro( Self );
protected: CommandIterationUpdate() {};
public: typedef itk::RegularStepGradientDescentOptimizer OptimizerType; typedef const OptimizerType * OptimizerPointer;
void Execute(itk::Object *caller, const itk::EventObject & event) { Execute((const itk::Object *)caller,event); }
void Execute(const itk::Object * object, const itk::EventObject & event) { OptimizerPointer optimizer = dynamic_cast< OptimizerPointer > ( object ); if( ! itk::IterationEvent().CheckEvent( &event)) { return; } std::cout << optimizer->GetCurrentIteration() << " " << std::endl; std::cout << optimizer->GetValue() << " " << std::endl; std::cout << optimizer->GetCurrentPosition() << " " << std::endl;
} };
int main() { const unsigned int Dimension = 2; typedef unsigned char PixelType;
typedef itk::Image<PixelType,Dimension> FixImageType; typedef itk::Image<PixelType,Dimension> MoveImageType;
typedef itk::TranslationTransform<double,Dimension> TransformType; typedef itk::LinearInterpolateImageFunction< MoveImageType , double > InterpolateType; typedef itk::MeanSquaresImageToImageMetric< FixImageType , MoveImageType > MetricType; typedef itk::RegularStepGradientDescentOptimizer OptimizerType; typedef itk::ImageRegistrationMethod< FixImageType , MoveImageType > RegistrationType;
TransformType::Pointer transform = TransformType::New(); InterpolateType::Pointer interpolator = InterpolateType::New(); MetricType::Pointer metric = MetricType::New(); OptimizerType::Pointer optimizer = OptimizerType::New(); RegistrationType::Pointer registration = RegistrationType::New();
registration->SetTransform( transform ); registration->SetInterpolator( interpolator ); registration->SetMetric( metric ); registration->SetOptimizer( optimizer );
typedef itk::ImageFileReader< FixImageType > FixedImageReaderType; typedef itk::ImageFileReader< MoveImageType > MoveImageReaderType;
FixedImageReaderType::Pointer fixedImageReader = FixedImageReaderType::New(); MoveImageReaderType::Pointer moveImageReader = MoveImageReaderType::New();
const char* FixedImageRoot = "D://pic//BFixed.png"; const char* MoveImageRoot = "D://pic//BMove2.png";
fixedImageReader->SetFileName( FixedImageRoot ); moveImageReader->SetFileName( MoveImageRoot );
registration->SetFixedImage( fixedImageReader->GetOutput()); registration->SetMovingImage( moveImageReader->GetOutput());
fixedImageReader->Update(); registration->SetFixedImageRegion( fixedImageReader->GetOutput()->GetBufferedRegion());
typedef RegistrationType::ParametersType ParametersType; ParametersType initialParameters( transform->GetNumberOfParameters() );
initialParameters[0] = 0.0; initialParameters[1] = 0.0;
registration->SetInitialTransformParameters ( initialParameters );
optimizer->SetMaximumStepLength ( 4.00 ); optimizer->SetMinimumStepLength ( 0.05 );
optimizer->SetNumberOfIterations( 200 );
CommandIterationUpdate::Pointer observer = CommandIterationUpdate::New();
optimizer->AddObserver( itk::IterationEvent(), observer );
try { registration->StartRegistration(); std::cout << "Optimizer stop condition: " << registration->GetOptimizer()->GetStopConditionDescription() << std::endl; } catch( itk::ExceptionObject &err ) { std::cerr << "ExceptionObject caught ! " << std::endl; std::cerr << err << std::endl; system("pause"); return -1; }
ParametersType finalParameters = registration->GetLastTransformParameters();
const double TranslationAlongX = finalParameters[0]; const double TranslationAlongY = finalParameters[1];
const unsigned int numberOfIterations = optimizer->GetCurrentIteration(); const double bestValue = optimizer->GetValue();
std::cout << " TranslationAlongX = " << TranslationAlongX << std::endl; std::cout << " TranslationAlongY = " << TranslationAlongY << std::endl;
std::cout << " numberOfIterations = " << numberOfIterations << std::endl;
system("pause");
typedef itk::ResampleImageFilter< MoveImageType , FixImageType > ResampleFilterType;
ResampleFilterType::Pointer resampler = ResampleFilterType::New(); resampler->SetInput( moveImageReader->GetOutput() );
resampler->SetTransform( registration->GetOutput()->Get() );
FixImageType::Pointer fixedImage = fixedImageReader->GetOutput(); resampler->SetSize( fixedImage->GetLargestPossibleRegion().GetSize() ); resampler->SetOutputOrigin( fixedImage->GetOrigin() ); resampler->SetOutputSpacing( fixedImage->GetSpacing() ); resampler->SetOutputDirection( fixedImage->GetDirection() ); resampler->SetDefaultPixelValue( 100 );
// typedef itk::ImageFileWriter< OutputImageType > WriterType; typedef itk::Image<PixelType,Dimension> OutputImageType; typedef itk::ImageFileWriter< OutputImageType > WriterType; WriterType::Pointer writer = WriterType::New(); //CastFilterType::Pointer caster = CastFilterType::New();
const char* writeFile = "D://pic//write.png"; writer->SetFileName( writeFile );
//caster->SetInput( resampler->GetOutput() ); //writer->SetInput( caster->GetOutput() ); writer->SetInput( resampler->GetOutput());
try { writer->Update();
} catch( itk::ExceptionObject &err ) { std::cerr << "ExceptionObject caught ! " << std::endl; std::cerr << err << std::endl; system("pause"); return -1; }
return 0 ;
}
|
8. Multi-Resolution Registration
Multi-Resolution配準方法，可以增強配準的準確性，速度以及魯棒性。如圖所示，它爲多次配準。採用金字塔模型，從第一次的粗糙配準到後面越來越細緻的配準，以此來達到程序的精確匹配。
代碼片段
|
void Execute(itk::Object * object, const itk::EventObject & event) { if(!(itk::IterationEvent().CheckEvent( &event ))) { return; } RegistrationPointer registration = dynamic_cast<RegistrationPointer>( object ); OptimizerPointer optimizer = dynamic_cast< OptimizerPointer >( registration->GetOptimizer() ); std::cout << "-------------------------------------" << std::endl; std::cout << "MultiResolution Level : " << registration->GetCurrentLevel() << std::endl; std::cout << std::endl;
if( registration->GetCurrentLevel() == 0 ) { optimizer->SetMaximumStepLength( 16.00 ); optimizer->SetMinimumStepLength( 0.01 ); } else { optimizer->SetMaximumStepLength( optimizer->GetMaximumStepLength() / 4.0 ); optimizer->SetMinimumStepLength( optimizer->GetMinimumStepLength() / 10.0 ); }
} |
9.Resample Image Filter
適用於配準後的圖像輸出.
Inputs: an image , transform , interpolator .
它針對的是空間座標系，而不是像素，單位是毫米。它是把像素點換算成座標點，然後再賦值的。
它的座標系起點爲左下角。