ImageDev

GrayscaleReconstruction2d

Performs a two-dimensional numerical reconstruction, starting from a grayscale marker image, into a grayscale input image.

Access to parameter description

For an introduction: This algorithm removes the light points in a dark image (reconstruction by dilation) or the dark points in a light image (reconstruction by erosion).

This algorithm is based on a recursive method whereby the minimum between the dilated or eroded image and the mask image is retained and used as the marker image for the next step.
At each step, the marker image is dilated or eroded by a structuring element of size 1.
This operation is repeated until stability. Therefore, the number of iterations depends on the input image and the marker image.

As shown in Figure 1, peaks and ridges are levelled down with a reconstruction by dilation, which results in a much more homogeneous output image.

<b> Figure 1.</b> One-dimensional example of a reconstruction by dilation
Figure 1. One-dimensional example of a reconstruction by dilation

As shown in Figure 2, the valleys are leveled up with a reconstruction by erosion, which results in a much more homogeneous output image.

<b> Figure 2.</b> One-dimensional example of a reconstruction by erosion
Figure 2. One-dimensional example of a reconstruction by erosion


See also

Function Syntax

This function returns outputImage. 
// Function prototype
std::shared_ptr< iolink::ImageView >
grayscaleReconstruction2d( std::shared_ptr< iolink::ImageView > inputImage,
                           std::shared_ptr< iolink::ImageView > inputMarkerImage,
                           GrayscaleReconstruction2d::ReconstructionType reconstructionType,
                           GrayscaleReconstruction2d::Neighborhood neighborhood,
                           std::shared_ptr< iolink::ImageView > outputImage = NULL );

Class Syntax

Parameters

Class Name GrayscaleReconstruction2d

Parameter Name Description Type Supported Values Default Value
input
inputImage
The grayscale input mask image constraining reconstruction. Image Binary, Label or Grayscale nullptr
input
inputMarkerImage
The grayscale input marker image containing seeds for reconstruction. It must have the same dimensions and type as the input image. Image Binary, Label, Grayscale or Multispectral nullptr
input
reconstructionType
The type of reconstruction algorithm to apply.
DILATION The reconstruction is performed by dilation. This mode removes the light points in a dark image.
EROSION The reconstruction is performed by dilation. This mode removes the dark points in a light image.
Enumeration DILATION
input
neighborhood
The 2D neighborhood configuration for performing dilations or erosions.
CONNECTIVITY_4 The structuring element is a cross.
CONNECTIVITY_8 The structuring element is a square.
Enumeration CONNECTIVITY_8
output
outputImage
The output image. Its dimensions and type are forced to the same values as the input. Image nullptr

Object Examples

std::shared_ptr< iolink::ImageView > polystyrene = ioformat::readImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene.tif" );

GrayscaleReconstruction2d grayscaleReconstruction2dAlgo;
grayscaleReconstruction2dAlgo.setInputImage( polystyrene );
grayscaleReconstruction2dAlgo.setInputMarkerImage( polystyrene );
grayscaleReconstruction2dAlgo.setReconstructionType( GrayscaleReconstruction2d::ReconstructionType::DILATION );
grayscaleReconstruction2dAlgo.setNeighborhood( GrayscaleReconstruction2d::Neighborhood::CONNECTIVITY_8 );
grayscaleReconstruction2dAlgo.execute();

std::cout << "outputImage:" << grayscaleReconstruction2dAlgo.outputImage()->toString();

Function Examples

std::shared_ptr< iolink::ImageView > polystyrene = ioformat::readImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene.tif" );

auto result = grayscaleReconstruction2d( polystyrene, polystyrene, GrayscaleReconstruction2d::ReconstructionType::DILATION, GrayscaleReconstruction2d::Neighborhood::CONNECTIVITY_8 );

std::cout << "outputImage:" << result->toString();