Extract Inner and Outer Boundaries of Blobs in Binary Image

Synopsis

Extract the inner and outer boundaries of blobs in a binary image.

Results

Output In VTK Window

Code

C++

#include "itkImage.h"
#include "itkImageFileWriter.h"
#include "itkInvertIntensityImageFilter.h"
#include "itkBinaryContourImageFilter.h"
#include "itkRescaleIntensityImageFilter.h"

#ifdef ENABLE_QUICKVIEW
#  include "QuickView.h"
#endif
using ImageType = itk::Image<unsigned char, 2>;

static void
CreateImage(ImageType::Pointer image);

int
main(int, char *[])
{
  ImageType::Pointer image = ImageType::New();
  CreateImage(image);

  using binaryContourImageFilterType = itk::BinaryContourImageFilter<ImageType, ImageType>;

  // Outer boundary
  binaryContourImageFilterType::Pointer binaryContourFilter = binaryContourImageFilterType::New();
  binaryContourFilter->SetInput(image);
  binaryContourFilter->SetForegroundValue(0);
  binaryContourFilter->SetBackgroundValue(255);
  binaryContourFilter->Update();

  // Invert the result
  using InvertIntensityImageFilterType = itk::InvertIntensityImageFilter<ImageType>;

  InvertIntensityImageFilterType::Pointer invertIntensityFilter = InvertIntensityImageFilterType::New();
  invertIntensityFilter->SetInput(binaryContourFilter->GetOutput());
  invertIntensityFilter->Update();

  ImageType::Pointer outerBoundary = ImageType::New();
  outerBoundary->Graft(invertIntensityFilter->GetOutput());

  // Inner boundary
  binaryContourFilter->SetForegroundValue(255);
  binaryContourFilter->SetBackgroundValue(0);
  binaryContourFilter->Update();

#ifdef ENABLE_QUICKVIEW
  QuickView viewer;
  viewer.AddImage(image.GetPointer());
  viewer.AddImage(outerBoundary.GetPointer());
  viewer.AddImage(binaryContourFilter->GetOutput());
  viewer.Visualize();
#endif
  return EXIT_SUCCESS;
}

void
CreateImage(ImageType::Pointer image)
{
  ImageType::IndexType start;
  start.Fill(0);

  ImageType::SizeType size;
  size.Fill(20);

  ImageType::RegionType region(start, size);

  image->SetRegions(region);
  image->Allocate();
  image->FillBuffer(0);

  // Make a square
  for (unsigned int r = 5; r < 10; r++)
  {
    for (unsigned int c = 5; c < 10; c++)
    {
      ImageType::IndexType pixelIndex;
      pixelIndex[0] = r;
      pixelIndex[1] = c;

      image->SetPixel(pixelIndex, 255);
    }
  }
}

Classes demonstrated

template<typename TInputImage, typename TOutputImage>
class BinaryContourImageFilter : public itk::InPlaceImageFilter<TInputImage, TOutputImage>, protected itk::ScanlineFilterCommon<TInputImage, TOutputImage>

Labels the pixels on the border of the objects in a binary image.

BinaryContourImageFilter takes a binary image as input, where the pixels in the objects are the pixels with a value equal to ForegroundValue. Only the pixels on the contours of the objects are kept. The pixels not on the border are changed to BackgroundValue.

The connectivity can be changed to minimum or maximum connectivity with SetFullyConnected(). Full connectivity produces thicker contours.

https://www.insight-journal.org/browse/publication/217

Author

Gaetan Lehmann. Biologie du Developpement et de la Reproduction, INRA de Jouy-en-Josas, France.

See

LabelContourImageFilter BinaryErodeImageFilter SimpleContourExtractorImageFilter

ITK Sphinx Examples:

• All ITK Sphinx Examples

• Extract Boundaries Of Connected Regions In Binary Image

• Extract Inner And Outer Boundaries Of Blobs In Binary Image

See itk::BinaryContourImageFilter for additional documentation.