Package com.openinventor.imageviz.engines.mathematicalmorphology.geodesictransformations

Class SoRegionalExtremaProcessing

  • All Implemented Interfaces:
    SafeDisposable
    public class SoRegionalExtremaProcessing
extends SoImageVizEngine
    SoRegionalExtremaProcessing engine. The SoRegionalExtremaProcessing engine computes the regional or relative fast maxima and minima in a grayscale image, , and displays the result in a binary image, . This algorithm is based on [1] and uses a recursive method combined with a geodesic propagation. To avoid getting too many regions in the output image, input should first be smoothed with a low-pass filter or with the dual numerical reconstruction algorithm.

    Case Minima

    This case of use computes the regional or relative minima in a grayscale image and creates a binary image containing these minima.

    A regional minimum is a set of connected pixels such that:

    • Pixels belonging to have the same intensity .
    • Pixels connected to , but not belonging to (neighbors), have an intensity greater than .

    Figure 1: Examples of regional minima in 1D.

    Case Maxima

    This engine computes the regional or relative maxima in a grayscale image and creates a binary image containing these maxima.

    A regional maximum is a set of connected pixels such that:

    • Pixels belonging to have the same intensity .
    • Pixels connected to , but not belonging to (neighbors), have an intensity greater than .

    Figure 2: Examples of regional maxima in 1 and 2D.

    [1] B. La. "Recursive Algorithms in Mathematical Morphology." In Acta Stereologica. Vol. 6/III, pp 691-696, Caen, France, Sept. 1987. 7th International Congress For Stereology.

    See Also:
    SoGrayscaleResconstructionProcessing File format/default: RegionalExtremaProcessing { computeMode MODE_AUTO neighborhood3d CONNECTIVITY_26 regionalOperator MAXIMA inImage NULL } Library references: fastmaxima fastminima