SoEigenvaluesToStructurenessProcessing2d Class Reference
[Edge Marking]

ImageViz SoEigenvaluesToStructurenessProcessing2d engine computes a structure score image More...

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

Inheritance diagram for SoEigenvaluesToStructurenessProcessing2d:
SoImageVizEngine SoEngine SoFieldContainer SoBase SoRefCounter SoTypedObject

List of all members.

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

ImageViz 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


Library references: EigenvaluesToStructureness2d


Member Enumeration Documentation

Enumerator:
BRIGHT 

Extracts bright structures from dark background.

DARK 

Extracts dark structures from bright background.

Enumerator:
ROD 

Extracts tubular structures.

BALL 

Extracts blob-like structures.


Constructor & Destructor Documentation

SoEigenvaluesToStructurenessProcessing2d::SoEigenvaluesToStructurenessProcessing2d (  ) 

Constructor.


Member Data Documentation

Blobness sensitivity threshold.

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

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.

The type of structure lightness to extract.

Use enum Lightness. Default is BRIGHT

Noise scale factor.

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

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.

Shape of structures to extract.

Use enum StructureType. Default is ROD


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

Open Inventor Toolkit reference manual, generated on 15 Mar 2023
Copyright © Thermo Fisher Scientific All rights reserved.
http://www.openinventor.com/