Blurring an Image Using a Binomial Kernel¶
Synopsis¶
The BinomialBlurImageFilter computes a nearest neighbor average along each dimension. The process is repeated a number of times, as specified by the user. In principle, after a large number of iterations the result will approach the convolution with a Gaussian.
Results¶
Code¶
Python¶
#!/usr/bin/env python
import itk
import argparse
parser = argparse.ArgumentParser(
description="Blurring An Image Using A Binomial Kernel."
)
parser.add_argument("input_image")
parser.add_argument("output_image")
parser.add_argument("number_of_repetitions", type=int)
args = parser.parse_args()
InputPixelType = itk.F
OutputPixelType = itk.UC
Dimension = 2
InputImageType = itk.Image[InputPixelType, Dimension]
OutputImageType = itk.Image[OutputPixelType, Dimension]
reader = itk.ImageFileReader[InputImageType].New()
reader.SetFileName(args.input_image)
binomialFilter = itk.BinomialBlurImageFilter.New(reader)
binomialFilter.SetRepetitions(args.number_of_repetitions)
rescaler = itk.RescaleIntensityImageFilter[InputImageType, OutputImageType].New()
rescaler.SetInput(binomialFilter.GetOutput())
rescaler.SetOutputMinimum(0)
rescaler.SetOutputMaximum(255)
writer = itk.ImageFileWriter[OutputImageType].New()
writer.SetFileName(args.output_image)
writer.SetInput(rescaler.GetOutput())
writer.Update()
C++¶
#include "itkImage.h"
#include "itkImageFileReader.h"
#include "itkImageFileWriter.h"
#include "itkRescaleIntensityImageFilter.h"
#include "itkBinomialBlurImageFilter.h"
int
main(int argc, char * argv[])
{
if (argc < 4)
{
std::cerr << "Usage: " << std::endl;
std::cerr << argv[0] << " inputImageFile outputImageFile numberOfRepetitions" << std::endl;
return EXIT_FAILURE;
}
using InputPixelType = float;
using OutputPixelType = float;
using InputImageType = itk::Image<InputPixelType, 2>;
using OutputImageType = itk::Image<OutputPixelType, 2>;
using FilterType = itk::BinomialBlurImageFilter<InputImageType, OutputImageType>;
FilterType::Pointer filter = FilterType::New();
using ReaderType = itk::ImageFileReader<InputImageType>;
ReaderType::Pointer reader = ReaderType::New();
reader->SetFileName(argv[1]);
const unsigned int repetitions = std::stoi(argv[3]);
filter->SetInput(reader->GetOutput());
filter->SetRepetitions(repetitions);
filter->Update();
using WritePixelType = unsigned char;
using WriteImageType = itk::Image<WritePixelType, 2>;
using RescaleFilterType = itk::RescaleIntensityImageFilter<OutputImageType, WriteImageType>;
RescaleFilterType::Pointer rescaler = RescaleFilterType::New();
rescaler->SetOutputMinimum(0);
rescaler->SetOutputMaximum(255);
using WriterType = itk::ImageFileWriter<WriteImageType>;
WriterType::Pointer writer = WriterType::New();
writer->SetFileName(argv[2]);
rescaler->SetInput(filter->GetOutput());
writer->SetInput(rescaler->GetOutput());
writer->Update();
return EXIT_SUCCESS;
}
Classes demonstrated¶
-
template<typename
TInputImage
, typenameTOutputImage
>
classBinomialBlurImageFilter
: public itk::ImageToImageFilter<TInputImage, TOutputImage> Performs a separable blur on each dimension of an image.
The binomial blur consists of a nearest neighbor average along each image dimension. The net result after n-iterations approaches convolution with a gaussian.
- ITK Sphinx Examples: