Voxels3d =	extractLocalExtrema3d (inImg3d,inFeaturesDistX,inFeaturesDistY,inFeaturesDistZ)
Voxels3d =	extractLocalExtrema3d (inImg3d,inFeaturesDistX,inFeaturesDistY,inFeaturesDistZ,localExtremaConfig)

Detailed Description

extraction of local extrema (minima or maxima) in a 3d image

This algorithm computes the local extrema (minimum or maximum, strict or not) for each 3d data of the input image.

In other words, the results will be computed :

for the whole grey level 3d volume,
for each channel of a color volume,
for each frame in a 3d sequence,
for each channel of each volume of a 3d sequence.

Two wrappers can be called : the extractLocalExtrema3d wrapper is only used to compute the extrema extraction on a grey level 3d volume, whereas the multiSlice_extractLocalExtrema3d wrapper must be used for more complex data (sequence and/or color).

See Local Extrema Extraction 2d for more details about the algorithm parameters.

Example of Python code :

Example imports

import PyIPSDK

import PyIPSDK.IPSDKIPLFeatureDetection as fd

Code Example

    # opening of input image
    inImg = PyIPSDK.loadTiffImageFile(inputImgPath)
    
    # half size neighbourhood definition
    halfSizeKnlX = 1
    halfSizeKnlY = 1
    halfSizeKnlZ = 1
    
    # local extrema configuration definition
    threshold = -30
    nbTotPoints = 2000
    localExtremaConfig = PyIPSDK.createLocalExtremaConfig(PyIPSDK.eLocalExtremumType.eLET_StrictMax, threshold, nbTotPoints)
   
    # local extrema computation
    outVoxels3d = fd.extractLocalExtrema3d(inImg, halfSizeKnlX, halfSizeKnlY, halfSizeKnlZ, localExtremaConfig)
     
    # retrieve coordinates of maximum detected extrema
    maxVoxel3d = PyIPSDK.toPyDict(outVoxels3d)['Coll'][0]
    print("Maximum extrema value " + str(maxVoxel3d['Intensity'] ) + " found on coordinates x=" + str(maxVoxel3d['X'] ) + ", y=" + str(maxVoxel3d['Y'] ) + " and z=" + str(maxVoxel3d['Z'] ))

Example of C++ code :

Example informations

Header file

#include <IPSDKIPL/IPSDKIPLFeatureDetection/Processor/ExtractLocalExtrema3d/ExtractLocalExtrema3d.h>

Code Example

    // ------------ Calculation on a mono-slice grey level image ------------ //
    // Create the local extrema configuration instance, specifying the local extremum type, 
    // the threshold and the number of total points. All these parameters are optional
    LocalExtremaConfigPtr pLocalExtremaConfig = createLocalExtremaConfig(localExtremumType, threshold, nbTotPoints);
    // Define the image geometry
    ImageGeometryPtr pInputImageGeometry = geometry3d(type, sizeX, sizeY, sizeZ);
    // Load the input image
    ImagePtr pInImg = loadRawImageFile(inImgFilePath, *pInputImageGeometry);
    // Extrcat the local extrema, in a given neighbourhood
    Voxels3dPtr pExtremaColl = extractLocalExtrema3d(pInImg, halfKnlSizeX, halfKnlSizeY, halfKnlSizeZ, pLocalExtremaConfig);
    // Retrieve the extrema collection
    const std::vector< boost::shared_ptr<Voxel3d> > extremaColl = pExtremaColl->getNodeColl<Voxels3d::Coll>();
    const ipUInt64 nbPoints = extremaColl.size();
    // ------------ Calculation on a multi-slice grey level image ------------ //
    // Extrcat the local extrema, in a given neighbourhood
    PlanIndexedVoxels3dPtr pExtremaColl_multiSlice = multiSlice_extractLocalExtrema3d(pInImg_multiSlice, halfKnlSizeX, halfKnlSizeY, halfKnlSizeZ, pLocalExtremaConfig);
    // Retrieve the extrema collection for the frame 2, the channel 1
    const std::vector< boost::shared_ptr<Voxel3d> > extremaColl_multiSlice = pExtremaColl_multiSlice->getValue(0, 1, 2).getNodeColl<Voxels3d::Coll>();