SoMultiscaleStructureEnhancementProcessing2d engine More...
#include <ImageViz/Engines/ImageFiltering/TextureFilters/SoMultiscaleStructureEnhancementProcessing2d.h>
Public Types  
enum  TensorType { HESSIAN = 0, GRADIENT = 1 } 
enum  Lightness { BRIGHT = 0, DARK = 1 } 
enum  StructureType { ROD = 0, BALL = 1 } 
Public Member Functions  
SoMultiscaleStructureEnhancementProcessing2d ()  
Public Attributes  
SoSFImageDataAdapter  inImage 
SoSFEnum  tensorType 
SoSFVec2f  standardDeviationRange 
SoSFFloat  standardDeviationStep 
SoSFEnum  lightness 
SoSFEnum  structureType 
SoImageVizEngineOutput < SoSFImageDataAdapter, SoImageDataAdapter * >  outImage 
The purpose of this algorithm is to enhance structures of interest from an image using a multi scale analysis. The result of this algorithm is a score image that can be used with the goal of segmenting the input image.
The SoMultiscaleStructureEnhancement filters compute a score between 0 and 1 for each pixel, 1 representing a good matching with a structure model and 0 a background pixel. This provides a powerful technique for automatically identifying structures such as blood vessels. The score can be computed either on an Hessian matrix to detect ridge structures or on a Gradient tensor for object edges and corners. The structure models available are:
The principle of the algorithm can be summarized as follows :
The following publication describes this algorithm when applied to detect Rod structures with the Hessian matrix: 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. 130137, 1998.
2 modes are available for computing the tensor field; the GRADIENT mode and the HESSIAN mode. The first one is based on the gradient tensor, the second one on the hessian matrix.
In the GRADIENT mode, the gradient tensor is extracted. This tensor also referred to as structure tensor or second order moment matrix, is a matrix derived from the gradient of the image. This matrix summarizes the predominant directions of the gradient around the voxel of interest.
Where is a gaussian kernel controlling the scale of analysis.
In this mode, the tensor field is based on the extraction of the hessian matrix of the image. This hessian matrix is computed by filtering the image with the derivative of a gaussian kernel. The standard deviation of the kernel controls the scale of analysis.
The parameter structureType controls the type of structure that is extracted from the tensor field (ROD/BALL). Let be the 2 eigenvalues of the extracted tensor.
The score for StructureType2D::ROD corresponds to :
This score favors anisotropic tensors.
The score for StructureType2D::BALL structures is computed as follows :
This score favors isotropic tensors.
where is the tensor norm, is a threshold which controls the blobness sensitivity, and c is a sensitivity threshold which controls the noise influence. with the maximum Hessian norm in the image.
In the HESSIAN mode, the lightness parameter limits the feature extraction to dark or bright objects by analyzing the sign of eigenvalues. This parameter is ignored in GRADIENT mode where tensors are positive definite matrices.
The table below summarizes enhanced feature according to the parameters
Structure Type 

 detected feature in GRADIENT mode  detected feature in HESSIAN mode 
ROD  strong  weak  straight edge  ridge 
BLOB  strong  strong  edge corner/blob  blob 
SoMultiscaleStructureEnhancementProcessing3d.
inImage  NULL 
tensorType  HESSIAN 
standardDeviationRange  1.0f 3.0f 
standardDeviationStep  1.0f 
lightness  BRIGHT 
structureType  ROD 
SoMultiscaleStructureEnhancementProcessing2d::SoMultiscaleStructureEnhancementProcessing2d  (  ) 
Constructor.
Input image.
Type of the image can be integer or floating. Default value is NULL. Supported types include: grayscale image.
The lightness type of structures to enhance.
Use enum Lightness. Default is BRIGHT
SoImageVizEngineOutput<SoSFImageDataAdapter, SoImageDataAdapter *> SoMultiscaleStructureEnhancementProcessing2d::outImage 
Output image.
Type of the output image is forced to float. Default value is NULL. Supported types include: grayscale image.
Standard deviation of the Gaussian kernel at minimum and maximum scale.
Default value is SbVec2f(1.0f,3.0f).
Standard deviation step.
Structures will be detected from min to max standard deviation at a pitch of this value. Default value is 1.0f.
Shape of structures to extract.
Use enum StructureType. Default is ROD
Defines whether the command will use the gradient tensor or the hessian matrix.
Use enum TensorType. Default is HESSIAN