SoLocalStatisticsProcessing Class Reference
[Texture Filters]

ImageViz SoLocalStatisticsProcessing engine More...

#include <ImageViz/Engines/ImageFiltering/TextureFilters/SoLocalStatisticsProcessing.h>

Inheritance diagram for SoLocalStatisticsProcessing:
SoImageVizEngine SoEngine SoFieldContainer SoBase SoRefCounter SoTypedObject

List of all members.

Public Types

enum  StatisticalOperator {
  MEAN = 0,
  ENERGY = 6,
enum  KernelShape {
  CUBE = 0,
  BALL = 1

Public Member Functions

 SoLocalStatisticsProcessing ()

Public Attributes

SoSFEnum computeMode
SoSFEnum statisticalOperator
SoSFImageDataAdapter inImage
SoSFInt32 kernelSize
SoSFEnum kernelShape
< SoSFImageDataAdapter,
SoImageDataAdapter * > 

Detailed Description

ImageViz SoLocalStatisticsProcessing engine

SoLocalStatisticsProcessing image filter computes statistics on a sliding window. The SoLocalStatisticsProcessing filter computes for each voxel of an image the value of a selected statistical operator on a predefined neighborhood. It creates a result image where output pixel values are only function of the corresponding pixel values in the input image and its neighborhood of a given size. These output values are extracted from local histograms which are arrays representing the number of pixels per value in the neighborhood. In the equations of each statistical operator description, $p(n)$ corresponds to the probability to have a pixel with value $n$ (i.e., the number of pixels of value $n$ divided by the total number of pixels in the neighborhood).

Available statistical operators are:


Library references: lcontrast lenergy lentropy lkurtosis lmean lskewness lvariance lvariation lcontrast3d lenergy3d lentropy3d lkurtosis3d lmean3d lskewness3d lvariance3d lvariation3d

Member Enumeration Documentation


The shape is a square in 2D mode or a cube in 3D mode.


The shape is a disk in 2D or a sphere in 3D mode.


The MEAN type gives to pixels the mean value in its neighbourhood:

\[mean=m=\sum_{n}n\cdot p(n)\]



The VARIANCE type gives to pixels the variance value in its neighbourhood:

\[variance=\sigma^2=\sum_{n}(n-m)^2\cdot p(n)\]



The SKEWNESS type gives to pixels the skewness value in its neighbourhood:

\[skewness=\frac{\sum\limits_{n}(n-m)^3\cdot p(n)}{\sigma^3}\]



The KURTOSIS type gives to pixels the kurtosis value in its neighbourhood:

\[kurtosis=\frac{\sum\limits_{n}(n-m)^4\cdot p(n)}{\sigma^4}-3\]



The CONTRAST type gives to pixels the contrast value in its neighbourhood:




The VARIATION type gives to pixels the variation value in its neighbourhood:




The ENERGY type gives to pixels the energy value in its neighbourhood in the reduced image:




The ENTROPY type gives to pixels the entropy of its neighbourhood in the reduced image:

\[entropy=-\sum_{n}p(n)\cdot\log p(n)\]


See also: SoCrossCorrelationProcessing2d

Constructor & Destructor Documentation

SoLocalStatisticsProcessing::SoLocalStatisticsProcessing (  ) 


Member Data Documentation

Select the compute Mode (2D or 3D or AUTO) Use enum ComputeMode.

Default is MODE_AUTO

The input image.

Default value is NULL. Supported types include: grayscale binary label color image.

Shape of the neighborhood.

Use enum KernelShape. Default is BALL

Specifies the size of the kernel.

The value of kernelSize is actually the 'half' kernel size. For example, kernelSize = 1 applies a 3x3(x3) pixel kernel in 2D(3D) when kernelShape is CUBE. Default value is 3.

The output image.

Default value is NULL. Supported types include: grayscale binary label color image.

Select the first order measure to compute.

Use enum StatisticalOperator. Default is MEAN

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

Open Inventor by FEI reference manual, generated on 20 Aug 2019
Copyright © FEI S.A.S. All rights reserved.