SoGaussianGradientTensorProcessing2d Class Reference
[Edge Marking]

ImageViz SoGaussianGradientTensorProcessing2d engine computes the structure tensor. More...

#include <ImageViz/Engines/EdgeDetection/EdgeMarking/SoGaussianGradientTensorProcessing2d.h>

Inheritance diagram for SoGaussianGradientTensorProcessing2d:
SoImageVizEngine SoEngine SoFieldContainer SoBase SoRefCounter SoTypedObject

List of all members.

Public Member Functions

 SoGaussianGradientTensorProcessing2d ()

Public Attributes

SoSFImageDataAdapter inImage
SoSFVec2f standardDeviation
SoImageVizEngineOutput
< SoSFImageDataAdapter,
SoImageDataAdapter * > 
outTensorImage

Detailed Description

ImageViz SoGaussianGradientTensorProcessing2d engine computes the structure tensor.

The SoGradientOperatorProcessing2d engine computes the structure tensor of the input image $\begin{pmatrix} I_x.I_x & I_x.I_y\\ I_x.I_y & I_y.I_y \end{pmatrix} = \begin{pmatrix} I_x\\ I_y\end{pmatrix} \cdot \begin{pmatrix} I_x & I_y\end{pmatrix}$ by convolving the input image with the square first order derivatives of a Gaussian Kernel.

For instance, $I_x = \frac{\partial I}{\partial x}$, $I_y = \frac{\partial I}{\partial x}$.

This filter provides an output spectral image where each channel represents a product of two partial derivative set in the following order $I_x.I_x$, $I_x.I_y$, $I_y.I_y$.

In order to extract the eigenvalues or vectors of the result image the SoEigenDecompositionProcessing2d command can be applied on the spectral image output.

SEE ALSO

SoEigenDecompositionProcessing2d, SoHessianMatrixProcessing2d, SoEigenvaluesToStructurenessProcessing2d.

FILE FORMAT/DEFAULT


Library references: GaussianGradientTensor2d


Constructor & Destructor Documentation

SoGaussianGradientTensorProcessing2d::SoGaussianGradientTensorProcessing2d (  ) 

Constructor.


Member Data Documentation

inImage Default value is NULL.

Supported types include: grayscale color image.

outTensorImage Default value is NULL.

Supported types include: grayscale binary label color image.

The standard deviation for each direction (X, Y) of the Gaussian Kernel that is used for computing first order derivatives.

Each value must be greater than or equal to 0.1. Default value is SbVec2f( 3.f, 3.f ).


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/