Main Page
Groups
Namespace List
Class Hierarchy
Alphabetical List
Compound List
File
List
Namespace Members
Compound Members
File Members
Concepts
itk::SimpleFuzzyConnectednessScalarImageFilter< TInputImage, TOutputImage > Class Template Reference
[Fuzzy Connectedness-based Segmentation Filters]
#include <itkSimpleFuzzyConnectednessScalarImageFilter.h>
List of all members.
Detailed Description
template<class TInputImage, class TOutputImage>
class itk::SimpleFuzzyConnectednessScalarImageFilter< TInputImage, TOutputImage >
/class FuzzyConnectednessRGBImageFilter
Perform the segmentation for a single channel (Grayscale) image via thresholding of a fuzzy connectedness scene. Used as a node of the segmentation toolkit. Fuzzy affinity is defined between two neighboor pixels, to reflect their similarity and assign a probability that these two pixels belong to the same object. A "path" between two pixels is a list of pixels that connect them, the strength of a particular path is defined as the weakest affinity between the neighboor pixels that form the path. The fuzzy connectedness between two pixels is defined as the strongest path strength between these two pixels. The segmentation based on fuzzy connectedness assumes that the fuzzy connectedness between any two pixels from a single object is significantly higher than those for pixels belonging to different objects. A fuzzy connectedness scene is first computed for a set of input seed points selected inside the object of interest. A threshold is then applied to the fuzzy scene to extract the binary segmented object. The fuzzy affinity here was defined as a gaussian function of the pixel difference and the difference of the estimated object mean and the mean of the two input pixels.
Input Parameters are: (1) Input image in the form itkImage (2) Seed points (3) Threshold value.
Usage: 1. use SetInput to import the input image object 2. use SetParameter, SetSeed, SetThreshold to set the parameters 3. run GenerateData() to perform the segmenation 4. threshold can be set using UpdateThreshold after the segmentation, and no computation will be redo. no need to run GenerateData. But if SetThreshold was used. MakeSegmentObject() should be called to get the updated result. 5. use GetOutput to obtain the resulted binary image Object. 6. GetFuzzyScene gives the pointer of Image<unsigned short> for the fuzzy scene.
Detailed information about this algorithm can be found in: "Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation", J. Udupa and S. Samarasekera Graphical Models and Image Processing, Vol.58, No.3. pp 246-261, 1996.
Definition at line 73 of file itkSimpleFuzzyConnectednessScalarImageFilter.h.
Member Typedef Documentation
Constructor & Destructor Documentation
Member Function Documentation
|
|
Run-time type information (and related methods). |
|
|
Get the Estimation of the mean difference between neighbor pixels for the object. |
|
|
Get the Estimation of the variance of the difference between pixels for the object. |
|
|
Get the Estimation of the mean difference between neighbor pixels for the object. |
|
|
Get the Estimation of the variance of the difference between pixels for the object. |
|
|
Method for creation through the object factory. |
|
|
Set the Estimation of the mean difference between neighbor pixels for the object. |
|
|
Set the Estimation of the variance of the difference between pixels for the object. |
|
|
Set the Estimation of the mean difference between neighbor pixels for the object. |
|
template<class TInputImage, class TOutputImage> |
| void itk::SimpleFuzzyConnectednessScalarImageFilter< TInputImage, TOutputImage >::SetParameters |
( |
const double |
inmean, |
|
|
const double |
invar, |
|
|
const double |
indifmean, |
|
|
const double |
indifvar, |
|
|
const double |
inweight |
|
) |
|
|
|
|
Setting the parameters for segmentation. |
|
|
Set the Estimation of the variance of the difference between pixels for the object. |
Member Data Documentation
The documentation for this class was generated from the following file:
Generated at Sat Mar 31 02:40:01 2007 for ITK by 
1.3.8 written by Dimitri van Heesch,
© 1997-2000