Class SoAutoIntensityClassificationProcessing

  • All Implemented Interfaces:
    SafeDisposable

    public class SoAutoIntensityClassificationProcessing
    extends SoImageVizEngine
    SoAutoIntensityClassificationProcessing classifies all pixels/voxels of an image using the k-means method. Given a set of observations (x1, x2, ..., xn), where each observation is a d-dimensional real vector, k-means clustering aims to partition the n observations into k (= n) sets S = {S1, S2, ..., Sk} so as to minimize the within-cluster sum of squares (WCSS) (sum of distance functions of each point in the cluster to the K center).

    References

    Lloyd, S. P. "Least square quantization in PCM." IEEE Transactions on Information Theory 28 (2): 129–137, 1982.

    File format/default:

    AutoIntensityClassificationProcessing {

      computeMode MODE_AUTO
      inImage NULL
      classNumber 2
      dataPercentage 100
    }


    Library references: k_means_classification

    • Field Detail

      • inImage

        public final SoSFImageDataAdapter inImage
        The input image. Default value is NULL. Supported types include: grayscale binary label color image.
      • classNumber

        public final SoSFInt32 classNumber
        The number of classes to detect (i.e. the label number of the output). Default value is 2.
      • dataPercentage

        public final SoSFInt32 dataPercentage
        The data percentage used for pre-computing the classification. Default value is 100.
    • Constructor Detail

      • SoAutoIntensityClassificationProcessing

        public SoAutoIntensityClassificationProcessing()
        Constructor.