Label Binary Regions in Image#

Synopsis#

Label binary regions in an image.

Results#

image.png

image.png#

Output:

There are 1 objects.
Object 0 contains pixel [6, 6]
Object 0 contains pixel [7, 6]
Object 0 contains pixel [8, 6]
Object 0 contains pixel [9, 6]
Object 0 contains pixel [6, 7]
Object 0 contains pixel [7, 7]
Object 0 contains pixel [8, 7]
Object 0 contains pixel [9, 7]
Object 0 contains pixel [6, 8]
Object 0 contains pixel [7, 8]
Object 0 contains pixel [8, 8]
Object 0 contains pixel [9, 8]
Object 0 contains pixel [6, 9]
Object 0 contains pixel [7, 9]
Object 0 contains pixel [8, 9]
Object 0 contains pixel [9, 9]

Code#

C++#

#include "itkImage.h"
#include "itkImageFileWriter.h"
#include "itkImageRegionIterator.h"
#include "itkBinaryImageToLabelMapFilter.h"

using ImageType = itk::Image<unsigned char, 2>;
static void
CreateImage(ImageType::Pointer image);

int
main()
{
  auto image = ImageType::New();
  CreateImage(image);

  using BinaryImageToLabelMapFilterType = itk::BinaryImageToLabelMapFilter<ImageType>;
  auto binaryImageToLabelMapFilter = BinaryImageToLabelMapFilterType::New();
  binaryImageToLabelMapFilter->SetInput(image);
  binaryImageToLabelMapFilter->Update();

  // The output of this filter is an itk::LabelMap, which contains itk::LabelObject's
  std::cout << "There are " << binaryImageToLabelMapFilter->GetOutput()->GetNumberOfLabelObjects() << " objects."
            << std::endl;

  // Loop over each region
  for (unsigned int i = 0; i < binaryImageToLabelMapFilter->GetOutput()->GetNumberOfLabelObjects(); ++i)
  {
    // Get the ith region
    BinaryImageToLabelMapFilterType::OutputImageType::LabelObjectType * labelObject =
      binaryImageToLabelMapFilter->GetOutput()->GetNthLabelObject(i);

    // Output the pixels composing the region
    for (unsigned int pixelId = 0; pixelId < labelObject->Size(); ++pixelId)
    {
      std::cout << "Object " << i << " contains pixel " << labelObject->GetIndex(pixelId) << std::endl;
    }
  }

  return EXIT_SUCCESS;
}

void
CreateImage(ImageType::Pointer image)
{
  // Create a black image with a white square
  ImageType::IndexType start;
  start.Fill(0);

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

  ImageType::RegionType region;
  region.SetSize(size);
  region.SetIndex(start);
  image->SetRegions(region);
  image->Allocate();

  itk::ImageRegionIterator<ImageType> imageIterator(image, image->GetLargestPossibleRegion());

  // Make a square
  while (!imageIterator.IsAtEnd())
  {
    if ((imageIterator.GetIndex()[0] > 5 && imageIterator.GetIndex()[0] < 10) &&
        (imageIterator.GetIndex()[1] > 5 && imageIterator.GetIndex()[1] < 10))
    {
      imageIterator.Set(255);
    }
    else
    {
      imageIterator.Set(0);
    }

    ++imageIterator;
  }

  itk::WriteImage(image, "image.png");
}

Classes demonstrated#

template<typename TInputImage, typename TOutputImage = LabelMap<LabelObject<SizeValueType, TInputImage::ImageDimension>>>
class BinaryImageToLabelMapFilter : public itk::ImageToImageFilter<TInputImage, TOutputImage>, protected itk::ScanlineFilterCommon<TInputImage, TOutputImage>

Label the connected components in a binary image and produce a collection of label objects.

BinaryImageToLabelMapFilter labels the objects in a binary image. Each distinct object is assigned a unique label. The final object labels start with 1 and are consecutive. Objects that are reached earlier by a raster order scan have a lower label.

The GetOutput() function of this class returns an itk::LabelMap.

This implementation was taken from the Insight Journal paper: https://www.insight-journal.org/browse/publication/176

Author

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

See

ConnectedComponentImageFilter, LabelImageToLabelMapFilter, LabelMap, LabelObject

ITK Sphinx Examples:

See itk::BinaryImageToLabelMapFilter for additional documentation.