Package com.openinventor.imageviz.engines.edgedetection.edgemarking

Class SoEigenvaluesToStructurenessProcessing2d

  • All Implemented Interfaces:
    SafeDisposable
    public class SoEigenvaluesToStructurenessProcessing2d
extends SoImageVizEngine
    SoEigenvaluesToStructurenessProcessing2d engine computes a structure score image. It allows to extract tubular or blob-like structures from dark or bright background.

    The computation is based on eigen values and where .

    The structure score for bright tubular structures corresponds to :

    and the score for bright blob-like structures is computed as follow :

    where is the Hessian norm ,
    is a threshold which controls the blobness sensitivity,
    and c is a sensitivity threshold wich controls the noise influence.
    with the maximum Hessian norm in the image.

    For dark objects the conditions on and are reversed.

    The method is referenced by Frangi publication
    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. 130-137, 1998.

    This engine provides output float grayscale image where each voxel intensity represents a structure score.

    File format/default:

    EigenvaluesToStructurenessProcessing2d {

      inEigenvaluesImage NULL
      lightness BRIGHT
      structureType ROD
      beta 0.75f
      noiseCutoff 0.5f
    }


    Library references: EigenvaluesToStructureness2d

    • Field Detail

      • inEigenvaluesImage

        public final SoSFImageDataAdapter inEigenvaluesImage
        Image containing input eigenvalues field. Type must be float. Spectral series size is 2 (channel 0 = largest Eigen value, channel 1 = smallest Eigen value). Default value is NULL. Supported types include: grayscale color image.

      • beta

        public final SoSFFloat beta
        Blobness sensitivity threshold. It corresponds to the term of the score equation. Default value is 0.75f.

      • noiseCutoff

        public final SoSFFloat noiseCutoff
        Noise scale factor. It is used for computing the c term of the score equation. Default value is 0.5f.

      • outImage

        public final SoImageVizEngineOutput<SoSFImageDataAdapter,​SoImageDataAdapter> outImage
        Output image. Size (except spectral series, only one), calibration and interpretation of the ouput image are forced to the same values as the input. Type is forced to float. All values are between 0 and 1. Default value is NULL. Supported types include: grayscale binary label color image.

    • Constructor Detail

      • SoEigenvaluesToStructurenessProcessing2d

        public SoEigenvaluesToStructurenessProcessing2d()
        Constructor.