SoEigenvaluesToStructurenessProcessing2d Class Reference
[Edge Marking]

SoEigenvaluesToStructurenessProcessing2d engine computes a structure score image More...

#include <ImageViz/Engines/EdgeDetection/EdgeMarking/SoEigenvaluesToStructurenessProcessing2d.h>

Inheritance diagram for SoEigenvaluesToStructurenessProcessing2d:

Public Types
enum	Lightness { BRIGHT = 0, DARK = 1 }
enum	StructureType { ROD = 0, BALL = 1 }
Public Member Functions
	SoEigenvaluesToStructurenessProcessing2d ()
Public Attributes
SoSFImageDataAdapter	inEigenvaluesImage
SoSFEnum	lightness
SoSFEnum	structureType
SoSFFloat	beta
SoSFFloat	noiseCutoff
SoImageVizEngineOutput < SoSFImageDataAdapter, SoImageDataAdapter * >	outImage

Detailed Description

SoEigenvaluesToStructurenessProcessing2d engine computes a structure score image

It allows to extract tubular or blob-like structures from dark or bright background.

The computation is based on eigen values $\lambda_{1}$ and $\lambda_{2}$ where $\mid \lambda_{1} \mid \geq \mid \lambda_{2} \mid$ .

The structure score for bright tubular structures corresponds to :

$score = \left\{ \begin{array}{l l} 0 & \quad \text{if $\lambda_{1} > 0$, }\\ exp(- \frac{ \big( \frac{\lambda_{2}}{\lambda_{1}} \big) ^{2} }{2 \beta^{2} } ) \big(1-exp \big(- \frac{S^{2}}{2c^{2}} \big) \big) \\ \end{array} \right.$

and the score for bright blob-like structures is computed as follow :

$score = \left\{ \begin{array}{l l} 0 & \quad \text{if $\lambda_{1} > 0$ or $\lambda_{2} > 0$, }\\ \big(1-exp(- \frac{ \big( \frac{\lambda_{2}}{\lambda_{1}} \big) ^{2} }{2 \beta^{2} } )\big) \big(1-exp \big(- \frac{S^{2}}{2c^{2}} \big) \big) \\ \end{array} \right.$

where $S$ is the Hessian norm $S = \sqrt{\lambda_{1}^{2}\lambda_{2}^{2}}$ ,
$\beta$ is a threshold which controls the blobness sensitivity,
and c is a sensitivity threshold wich controls the noise influence.
$c = noiseCutoff*S_{max}$ with $S_{max}$ the maximum Hessian norm in the image.

For dark objects the conditions on $\lambda_{1}$ and $\lambda_{2}$ are reversed.

The method is referenced by Frangi publication
A.F.Frangi, W.J.Niessen, K.L.Vincken, M.A.Viergever, "Multiscale vessel enhancement filtering"
Lecture Notes in Computer Science(MICCAI), vol. 1496, pp. 130-137, 1998.

This engine provides output float grayscale image where each voxel intensity represents a structure score.

FILE FORMAT/DEFAULT

inEigenvaluesImage	NULL
lightness	BRIGHT
structureType	ROD
beta	0.75f
noiseCutoff	0.5f

Library references: EigenvaluesToStructureness2d

Member Enumeration Documentation

enum SoEigenvaluesToStructurenessProcessing2d::Lightness

Enumerator:

BRIGHT	Extracts bright structures from dark background.
DARK	Extracts dark structures from bright background.

enum SoEigenvaluesToStructurenessProcessing2d::StructureType

Enumerator:

ROD	Extracts tubular structures.
BALL	Extracts blob-like structures.

Constructor & Destructor Documentation

SoEigenvaluesToStructurenessProcessing2d::SoEigenvaluesToStructurenessProcessing2d ( )

Constructor.

Member Data Documentation

SoSFFloat SoEigenvaluesToStructurenessProcessing2d::beta

Blobness sensitivity threshold.

It corresponds to the $\beta$ term of the score equation. Default value is 0.75f.

SoSFImageDataAdapter SoEigenvaluesToStructurenessProcessing2d::inEigenvaluesImage

Image containing input eigenvalues field.

Type must be float. Spectral series size is 2 (channel 0 = largest Eigen value, channel 1 = smallest Eigen value). Default value is NULL. Supported types include: grayscale color image.

SoSFEnum SoEigenvaluesToStructurenessProcessing2d::lightness

The type of structure lightness to extract.

Use enum Lightness. Default is BRIGHT

SoSFFloat SoEigenvaluesToStructurenessProcessing2d::noiseCutoff

Noise scale factor.

It is used for computing the c term of the score equation. Default value is 0.5f.

SoImageVizEngineOutput<SoSFImageDataAdapter,SoImageDataAdapter*> SoEigenvaluesToStructurenessProcessing2d::outImage

Output image.

Size (except spectral series, only one), calibration and interpretation of the ouput image are forced to the same values as the input. Type is forced to float. All values are between 0 and 1. Default value is NULL. Supported types include: grayscale binary label color image.

SoSFEnum SoEigenvaluesToStructurenessProcessing2d::structureType

Shape of structures to extract.

Use enum StructureType. Default is ROD

The documentation for this class was generated from the following file:

ImageViz/Engines/EdgeDetection/EdgeMarking/SoEigenvaluesToStructurenessProcessing2d.h

SoEigenvaluesToStructurenessProcessing2d Class Reference [Edge Marking]

Public Types