open_iA  2020.04
A tool for the visual analysis and processing of volumetric datasets, with a focus on industrial computed tomography.
Classes | Enumerations
iAParametrizableLabelVotingImageFilter.h File Reference
#include <itkImageToImageFilter.h>
#include "iAParametrizableLabelVotingImageFilter.hxx"
Include dependency graph for iAParametrizableLabelVotingImageFilter.h:
This graph shows which files directly or indirectly include this file:

Classes

class  iAParametrizableLabelVotingImageFilter< TInputImage, TOutputImage >
 This filter performs pixelwise voting among an arbitrary number of input images, where each of them represents a segmentation of the same scene (i.e., image). More...
 

Enumerations

enum  OutputNumber { AbsolutePercentage, DiffPercentage, Ratio, PixelEntropy }
 
enum  WeightType { Equal, LabelBased, Certainty, FBGSBGDiff }
 

Enumeration Type Documentation

◆ OutputNumber

Enumerator
AbsolutePercentage 
DiffPercentage 
Ratio 
PixelEntropy 

◆ WeightType

enum WeightType
Enumerator
Equal 
LabelBased 

every considered input gets equal vote

Certainty 

an input gets for each pixel a weight based on input idx and label at that pixel (these weights need to be passed in via SetInputLabelWeights() method)

FBGSBGDiff 

an input is weighted based on the certainty (= inverse entropy) at that pixel (requires probabilities to be set via

an input is weighted based on the difference between first and second best guess