ImageDev

ReconstructionFromMarkers3d

ReconstructionFromMarkers3d rebuilds a binary image starting from markers.

Access to parameter description

For an introduction: This algorithm rebuilds a set of objects identified by markers and retrieves only the objects that contain at least one marker.

Successive dilations are performed on the markers, each dilation being followed by an intersection with the original image until convergence (idempotence).
This iterative process is called a geodesic dilation.
It guarantees that a dilated marker will not merge with a particle other than the one it marks.

Geodesic dilation is different from a large dilation of a given size followed by an intersection with the original image because a dilated marker may hit close particles that are not marked for reconstruction. This difference is illustrated in Figure 1.

For example, given an erosion that eliminated the small particles of an image, this algorithm can rebuild the original shapes of the remaining particles if the eroded set is used as the markers. This sequence is called an opening by reconstruction.

<b> Figure 1.</b> Comparison between reconstruction from markers and dilation/intersection
Figure 1. Comparison between reconstruction from markers and dilation/intersection


See also

Function Syntax

This function returns outputImage. 
// Function prototype
std::shared_ptr< iolink::ImageView >
reconstructionFromMarkers3d( std::shared_ptr< iolink::ImageView > inputImage,
                             std::shared_ptr< iolink::ImageView > inputMarkerImage,
                             ReconstructionFromMarkers3d::Neighborhood neighborhood,
                             std::shared_ptr< iolink::ImageView > outputImage = NULL );

Class Syntax

Parameters

Parameter Name Description Type Supported Values Default Value
input
inputImage
The binary mask image constraining reconstruction. Image Binary nullptr
input
inputMarkerImage
The binary marker image containing seeds for reconstruction. It must have the same dimensions and type as the input image. Image Binary nullptr
input
neighborhood
The 3D neighborhood configuration.
CONNECTIVITY_6 The structuring element is composed of voxels with a common face with the voxel of interest.
CONNECTIVITY_18 The structuring element is composed of voxels with at least one common edge.
CONNECTIVITY_26 The structuring element is a full cube.
Enumeration CONNECTIVITY_26
output
outputImage
The binary output image. Its dimensions and type are forced to the same values as the input. Image nullptr

Object Examples

auto polystyrene_sep = readVipImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene_sep.vip" );

ReconstructionFromMarkers3d reconstructionFromMarkers3dAlgo;
reconstructionFromMarkers3dAlgo.setInputImage( polystyrene_sep );
reconstructionFromMarkers3dAlgo.setInputMarkerImage( polystyrene_sep );
reconstructionFromMarkers3dAlgo.setNeighborhood( ReconstructionFromMarkers3d::Neighborhood::CONNECTIVITY_26 );
reconstructionFromMarkers3dAlgo.execute();

std::cout << "outputImage:" << reconstructionFromMarkers3dAlgo.outputImage()->toString();

Function Examples

auto polystyrene_sep = readVipImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene_sep.vip" );

auto result = reconstructionFromMarkers3d( polystyrene_sep, polystyrene_sep, ReconstructionFromMarkers3d::Neighborhood::CONNECTIVITY_26 );

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