[ VIGRA Homepage | Function Index | Class Index | Namespaces | File List | Main Page ]

details Region Segmentation Algorithms VIGRA

Classes

class  SeedOptions
 Options object for generateWatershedSeeds(). More...
class  SeedRgDirectValueFunctor< Value >
 Statistics functor to be used for seeded region growing. More...
class  WatershedOptions
 Options object for watershedsRegionGrowing(). More...

Enumerations

enum  SRGType

Functions

template<... >
unsigned int generateWatershedSeeds (...)
 Generate seeds for watershed computation and seeded region growing.
template<... >
unsigned int generateWatershedSeeds3D (...)
 Generate seeds for watershed computation and seeded region growing.
template<... >
void seededRegionGrowing (...)
 Region Segmentation by means of Seeded Region Growing.
template<... >
void seededRegionGrowing3D (...)
 Three-dimensional Region Segmentation by means of Seeded Region Growing.
template<... >
unsigned int watersheds3D (...)
 Region Segmentation by means of the watershed algorithm.
template<... >
unsigned int watershedsRegionGrowing (...)
 Region segmentation by means of a flooding-based watershed algorithm.
template<... >
unsigned int watershedsUnionFind (...)
 Region segmentation by means of the union-find watershed algorithm.


Detailed Description

Region growing, watersheds, and voronoi tesselation


Enumeration Type Documentation

enum SRGType

Choose between different types of Region Growing


Function Documentation

void vigra::seededRegionGrowing (   ...  ) 

Region Segmentation by means of Seeded Region Growing.

This algorithm implements seeded region growing as described in

R. Adams, L. Bischof: "<em> Seeded Region Growing</em>", IEEE Trans. on Pattern Analysis and Maschine Intelligence, vol 16, no 6, 1994, and

Ullrich Köthe: Primary Image Segmentation, in: G. Sagerer, S. Posch, F. Kummert (eds.): Mustererkennung 1995, Proc. 17. DAGM-Symposium, Springer 1995

The seed image is a partly segmented image which contains uniquely labeled regions (the seeds) and unlabeled pixels (the candidates, label 0). The highest seed label found in the seed image is returned by the algorithm.

Seed regions can be as large as you wish and as small as one pixel. If there are no candidates, the algorithm will simply copy the seed image into the output image. Otherwise it will aggregate the candidates into the existing regions so that a cost function is minimized. Candidates are taken from the neighborhood of the already assigned pixels, where the type of neighborhood is determined by parameter neighborhood which can take the values FourNeighborCode() (the default) or EightNeighborCode(). The algorithm basically works as follows (illustrated for 4-neighborhood, but 8-neighborhood works in the same way):

  1. Find all candidate pixels that are 4-adjacent to a seed region. Calculate the cost for aggregating each candidate into its adjacent region and put the candidates into a priority queue.

  2. While( priority queue is not empty and termination criterion is not fulfilled)

    1. Take the candidate with least cost from the queue. If it has not already been merged, merge it with it's adjacent region.

    2. Put all candidates that are 4-adjacent to the pixel just processed into the priority queue.

SRGType can take the following values:

CompleteGrow
produce a complete tesselation of the volume (default).
KeepContours
keep a 1-voxel wide unlabeled contour between all regions.
StopAtThreshold
stop when the boundary indicator values exceed the threshold given by parameter max_cost.
KeepContours | StopAtThreshold
keep 1-voxel wide contour and stop at given max_cost.

The cost is determined jointly by the source image and the region statistics functor. The source image contains feature values for each pixel which will be used by the region statistics functor to calculate and update statistics for each region and to calculate the cost for each candidate. The RegionStatisticsArray must be compatible to the ArrayOfRegionStatistics functor and contains an array of statistics objects for each region. The indices must correspond to the labels of the seed regions. The statistics for the initial regions must have been calculated prior to calling seededRegionGrowing() (for example by means of inspectTwoImagesIf()).

For each candidate x that is adjacent to region i, the algorithm will call stats[i].cost(as(x)) to get the cost (where x is a SrcIterator and as is the SrcAccessor). When a candidate has been merged with a region, the statistics are updated by calling stats[i].operator()(as(x)). Since the RegionStatisticsArray is passed by reference, this will overwrite the original statistics.

If a candidate could be merged into more than one regions with identical cost, the algorithm will favour the nearest region. If StopAtThreshold is active, and the cost of the current candidate at any point in the algorithm exceeds the optional max_cost value (which defaults to NumericTraits<double>::max()), region growing is aborted, and all voxels not yet assigned to a region remain unlabeled.

In some cases, the cost only depends on the feature value of the current pixel. Then the update operation will simply be a no-op, and the cost() function returns its argument. This behavior is implemented by the SeedRgDirectValueFunctor. With SRGType == KeepContours, this is equivalent to the watershed algorithm.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class SeedImageIterator, class SeedAccessor,
                  class DestIterator, class DestAccessor,
                  class RegionStatisticsArray, class Neighborhood>
        typename SeedAccessor::value_type 
        seededRegionGrowing(SrcIterator srcul, SrcIterator srclr, SrcAccessor as,
                            SeedImageIterator seedsul, SeedAccessor aseeds,
                            DestIterator destul, DestAccessor ad,
                            RegionStatisticsArray & stats,
                            SRGType srgType = CompleteGrow,
                            Neighborhood neighborhood = FourNeighborCode(),
                            double max_cost = NumericTraits<double>::max());
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class SeedImageIterator, class SeedAccessor,
                  class DestIterator, class DestAccessor,
                  class RegionStatisticsArray, class Neighborhood>
        typename SeedAccessor::value_type
        seededRegionGrowing(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                            pair<SeedImageIterator, SeedAccessor> seeds,
                            pair<DestIterator, DestAccessor> dest,
                            RegionStatisticsArray & stats,
                            SRGType srgType = CompleteGrow,
                            Neighborhood neighborhood = FourNeighborCode(),
                            double max_cost = NumericTraits<double>::max());
    }

Usage:

#include <vigra/seededregiongrowing.hxx>
Namespace: vigra

Example: implementation of the voronoi tesselation

    vigra::BImage points(w,h);
    vigra::FImage dist(x,y);

    // empty edge image
    points = 0;
    dist = 0;

    int max_region_label = 100;

    // throw in some random points:
    for(int i = 1; i <= max_region_label; ++i)
           points(w * rand() / RAND_MAX , h * rand() / RAND_MAX) = i;

    // calculate Euclidean distance transform
    vigra::distanceTransform(srcImageRange(points), destImage(dist), 2);

    // init statistics functor
    vigra::ArrayOfRegionStatistics<vigra::SeedRgDirectValueFunctor<float> >
                                              stats(max_region_label);

    // find voronoi region of each point
    vigra:: seededRegionGrowing(srcImageRange(dist), srcImage(points),
                               destImage(points), stats);

Required Interface:

    SrcIterator src_upperleft, src_lowerright;
    SeedImageIterator seed_upperleft;
    DestIterator dest_upperleft;

    SrcAccessor src_accessor;
    SeedAccessor seed_accessor;
    DestAccessor dest_accessor;

    RegionStatisticsArray stats;

    // calculate costs
    RegionStatisticsArray::value_type::cost_type cost =
        stats[seed_accessor(seed_upperleft)].cost(src_accessor(src_upperleft));

    // compare costs
    cost < cost;

    // update statistics
    stats[seed_accessor(seed_upperleft)](src_accessor(src_upperleft));

    // set result
    dest_accessor.set(seed_accessor(seed_upperleft), dest_upperleft);

Further requirements are determined by the RegionStatisticsArray.

Examples:
voronoi.cxx, and watershed.cxx.
void vigra::seededRegionGrowing3D (   ...  ) 

Three-dimensional Region Segmentation by means of Seeded Region Growing.

This algorithm implements seeded region growing as described in

The seed image is a partly segmented multi-dimensional array which contains uniquely labeled regions (the seeds) and unlabeled voxels (the candidates, label 0). Seed regions can be as large as you wish and as small as one voxel. If there are no candidates, the algorithm will simply copy the seed array into the output array. Otherwise it will aggregate the candidates into the existing regions so that a cost function is minimized. Candidates are taken from the neighborhood of the already assigned pixels, where the type of neighborhood is determined by parameter neighborhood which can take the values NeighborCode3DSix() (the default) or NeighborCode3DTwentySix(). The algorithm basically works as follows (illustrated for 6-neighborhood, but 26-neighborhood works in the same way):

  1. Find all candidate pixels that are 6-adjacent to a seed region. Calculate the cost for aggregating each candidate into its adjacent region and put the candidates into a priority queue.

  2. While( priority queue is not empty)

    1. Take the candidate with least cost from the queue. If it has not already been merged, merge it with it's adjacent region.

    2. Put all candidates that are 4-adjacent to the pixel just processed into the priority queue.

SRGType can take the following values:

CompleteGrow
produce a complete tesselation of the volume (default).
KeepContours
keep a 1-voxel wide unlabeled contour between all regions.
StopAtThreshold
stop when the boundary indicator values exceed the threshold given by parameter max_cost.
KeepContours | StopAtThreshold
keep 1-voxel wide contour and stop at given max_cost.

The cost is determined jointly by the source array and the region statistics functor. The source array contains feature values for each pixel which will be used by the region statistics functor to calculate and update statistics for each region and to calculate the cost for each candidate. The RegionStatisticsArray must be compatible to the ArrayOfRegionStatistics functor and contains an array of statistics objects for each region. The indices must correspond to the labels of the seed regions. The statistics for the initial regions must have been calculated prior to calling seededRegionGrowing3D()

For each candidate x that is adjacent to region i, the algorithm will call stats[i].cost(as(x)) to get the cost (where x is a SrcImageIterator and as is the SrcAccessor). When a candidate has been merged with a region, the statistics are updated by calling stats[i].operator()(as(x)). Since the RegionStatisticsArray is passed by reference, this will overwrite the original statistics.

If a candidate could be merged into more than one regions with identical cost, the algorithm will favour the nearest region. If StopAtThreshold is active, and the cost of the current candidate at any point in the algorithm exceeds the optional max_cost value (which defaults to NumericTraits<double>::max()), region growing is aborted, and all voxels not yet assigned to a region remain unlabeled.

In some cases, the cost only depends on the feature value of the current voxel. Then the update operation will simply be a no-op, and the cost() function returns its argument. This behavior is implemented by the SeedRgDirectValueFunctor.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcImageIterator, class Shape, class SrcAccessor,
                  class SeedImageIterator, class SeedAccessor,
                  class DestImageIterator, class DestAccessor,
                  class RegionStatisticsArray, class Neighborhood>
        void 
        seededRegionGrowing3D(SrcImageIterator srcul, Shape shape, SrcAccessor as,
                              SeedImageIterator seedsul, SeedAccessor aseeds,
                              DestImageIterator destul, DestAccessor ad,
                              RegionStatisticsArray & stats, 
                              SRGType srgType = CompleteGrow,
                              Neighborhood neighborhood = NeighborCode3DSix(),
                              double max_cost = NumericTraits<double>::max());
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcImageIterator, class Shape, class SrcAccessor,
                  class SeedImageIterator, class SeedAccessor,
                  class DestImageIterator, class DestAccessor,
                  class RegionStatisticsArray, class Neighborhood>
        void
        seededRegionGrowing3D(triple<SrcImageIterator, Shape, SrcAccessor> src,
                              pair<SeedImageIterator, SeedAccessor> seeds,
                              pair<DestImageIterator, DestAccessor> dest,
                              RegionStatisticsArray & stats, 
                              SRGType srgType = CompleteGrow,
                              Neighborhood neighborhood = NeighborCode3DSix(), 
                              double max_cost = NumericTraits<double>::max());
    }
unsigned int vigra::generateWatershedSeeds (   ...  ) 

Generate seeds for watershed computation and seeded region growing.

The source image is a boundary indicator such as the gradient magnitude or the trace of the boundaryTensor(). Seeds are generally generated at locations where the boundaryness (i.e. the likelihood of the point being on the boundary) is very small. In particular, seeds can be placed by either looking for local minima (possibly including minimal plateaus) of the boundaryness, of by looking at level sets (i.e. regions where the boundaryness is below a threshold). Both methods can also be combined, so that only minima below a threshold are returned. The particular seeding strategy is specified by the options object (see SeedOptions).

The pixel type of the input image must be LessThanComparable. The pixel type of the output image must be large enough to hold the labels for all seeds. (typically, you will use UInt32). The function will label seeds by consecutive integers (starting from 1) and returns the largest label it used.

Pass vigra::EightNeighborCode or vigra::FourNeighborCode to determine the neighborhood where pixel values are compared.

The function uses accessors.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        generateWatershedSeeds(SrcIterator upperlefts, SrcIterator lowerrights, SrcAccessor sa,
                               DestIterator upperleftd, DestAccessor da, 
                               Neighborhood neighborhood = EightNeighborCode(),
                               SeedOptions const & options = SeedOptions());
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        generateWatershedSeeds(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                               pair<DestIterator, DestAccessor> dest, 
                               Neighborhood neighborhood = EightNeighborCode(),
                               SeedOptions const & options = SeedOptions());
    }

Usage:

#include <vigra/watersheds.hxx>
Namespace: vigra

For detailed examples see watershedsRegionGrowing().

unsigned int vigra::watershedsUnionFind (   ...  ) 

Region segmentation by means of the union-find watershed algorithm.

This function implements the union-find version of the watershed algorithms as described in

J. Roerdink, R. Meijster: "<em>The watershed transform: definitions, algorithms, and parallelization strategies</em>", Fundamenta Informaticae, 41:187-228, 2000

The source image is a boundary indicator such as the gaussianGradientMagnitude() or the trace of the boundaryTensor(). Local minima of the boundary indicator are used as region seeds, and all other pixels are recursively assigned to the same region as their lowest neighbor. Pass vigra::EightNeighborCode or vigra::FourNeighborCode to determine the neighborhood where pixel values are compared. The pixel type of the input image must be LessThanComparable. The function uses accessors.

Note that VIGRA provides an alternative implementation of the watershed transform via watershedsRegionGrowing(). It is slower, but offers many more configuration options.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        watershedsUnionFind(SrcIterator upperlefts, SrcIterator lowerrights, SrcAccessor sa,
                            DestIterator upperleftd, DestAccessor da,
                            Neighborhood neighborhood = EightNeighborCode())
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        watershedsUnionFind(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                            pair<DestIterator, DestAccessor> dest,
                            Neighborhood neighborhood = EightNeighborCode())
    }

Usage:

#include <vigra/watersheds.hxx>
Namespace: vigra

Example: watersheds of the gradient magnitude.

    vigra::BImage in(w,h);
    ... // read input data

    // compute gradient magnitude as boundary indicator
    vigra::FImage gradMag(w, h);
    gaussianGradientMagnitude(srcImageRange(src), destImage(gradMag), 3.0);

    // the pixel type of the destination image must be large enough to hold
    // numbers up to 'max_region_label' to prevent overflow
    vigra::IImage labeling(w,h);
    int max_region_label = watershedsUnionFind(srcImageRange(gradMag), destImage(labeling));

Required Interface:

    SrcIterator src_upperleft, src_lowerright;
    DestIterator dest_upperleft;

    SrcAccessor src_accessor;
    DestAccessor dest_accessor;

    // compare src values
    src_accessor(src_upperleft) <= src_accessor(src_upperleft)

    // set result
    int label;
    dest_accessor.set(label, dest_upperleft);
unsigned int vigra::watershedsRegionGrowing (   ...  ) 

Region segmentation by means of a flooding-based watershed algorithm.

This function implements variants of the watershed algorithm described in

L. Vincent and P. Soille: "<em>Watersheds in digital spaces: An efficient algorithm based on immersion simulations</em>", IEEE Trans. Patt. Analysis Mach. Intell. 13(6):583-598, 1991

The source image is a boundary indicator such as the gaussianGradientMagnitude() or the trace of the boundaryTensor(), and the destination is a label image designating membership of each pixel in one of the regions. Plateaus in the boundary indicator (i.e. regions of constant gray value) are handled via a Euclidean distance transform by default.

By default, the destination image is assumed to hold seeds for a seeded watershed transform. Seeds may, for example, be created by means of generateWatershedSeeds(). Note that the seeds will be overridden with the final watershed segmentation.

Alternatively, you may provide SeedOptions in order to instruct watershedsRegionGrowing() to generate its own seeds (it will call generateWatershedSeeds() internally). In that case, the destination image should be zero-initialized.

You can specify the neighborhood system to be used by passing FourNeighborCode or EightNeighborCode (default).

Further options to be specified via WatershedOptions are:

  • Whether to keep a 1-pixel-wide contour (with label 0) between regions or perform complete grow (i.e. all pixels are assigned to a region).
  • Whether to stop growing when the boundaryness exceeds a threshold (remaining pixels keep label 0).
  • Whether to use a faster, but less powerful algorithm ("turbo algorithm"). It is faster because it orders pixels by means of a BucketQueue (therefore, the boundary indicator must contain integers in the range [0, ..., bucket_count-1], where bucket_count is specified in the options object), it only supports complete growing (no contour between regions is possible), and it handles plateaus in a simplistic way. It also saves some memory because it allocates less temporary storage.
  • Whether one region (label) is to be preferred or discouraged by biasing its cost with a given factor (smaller than 1 for preference, larger than 1 for discouragement).

Note that VIGRA provides an alternative implementation of the watershed transform via watershedsUnionFind().

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        watershedsRegionGrowing(SrcIterator upperlefts, SrcIterator lowerrights, SrcAccessor sa,
                                DestIterator upperleftd, DestAccessor da, 
                                Neighborhood neighborhood = EightNeighborCode(),
                                WatershedOptions const & options = WatershedOptions());

        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor>
        unsigned int
        watershedsRegionGrowing(SrcIterator upperlefts, SrcIterator lowerrights, SrcAccessor sa,
                                DestIterator upperleftd, DestAccessor da, 
                                WatershedOptions const & options = WatershedOptions());
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        watershedsRegionGrowing(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                                pair<DestIterator, DestAccessor> dest, 
                                Neighborhood neighborhood = EightNeighborCode(),
                                WatershedOptions const & options = WatershedOptions());
                                
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor>
        unsigned int
        watershedsRegionGrowing(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                                pair<DestIterator, DestAccessor> dest, 
                                WatershedOptions const & options = WatershedOptions());
    }

Usage:

#include <vigra/watersheds.hxx>
Namespace: vigra

Example: watersheds of the gradient magnitude.

    vigra::BImage src(w, h);
    ... // read input data
    
    // compute gradient magnitude at scale 1.0 as a boundary indicator
    vigra::FImage gradMag(w, h);
    gaussianGradientMagnitude(srcImageRange(src), destImage(gradMag), 1.0);

    // example 1
    {
        // the pixel type of the destination image must be large enough to hold
        // numbers up to 'max_region_label' to prevent overflow
        vigra::IImage labeling(w, h);
        
        // call watershed algorithm for 4-neighborhood, leave a 1-pixel boundary between regions,
        // and autogenerate seeds from all gradient minima where the magnitude is below 2.0
        unsigned int max_region_label = 
              watershedsRegionGrowing(srcImageRange(gradMag), destImage(labeling),
                                      FourNeighborCode(),
                                      WatershedOptions().keepContours()
                                           .seedOptions(SeedOptions().minima().threshold(2.0)));
    }
    
    // example 2
    {
        vigra::IImage labeling(w, h);
        
        // compute seeds beforehand (use connected components of all pixels 
        // where the gradient  is below 4.0)
        unsigned int max_region_label = 
              generateWatershedSeeds(srcImageRange(gradMag), destImage(labeling),
                                     SeedOptions().levelSets(4.0));
        
        // quantize the gradient image to 256 gray levels
        vigra::BImage gradMag256(w, h);
        vigra::FindMinMax<float> minmax; 
        inspectImage(srcImageRange(gradMag), minmax); // find original range
        transformImage(srcImageRange(gradMag), destImage(gradMag256),
                       linearRangeMapping(minmax, 0, 255));
        
        // call the turbo algorithm with 256 bins, using 8-neighborhood
        watershedsRegionGrowing(srcImageRange(gradMag256), destImage(labeling),
                                WatershedOptions().turboAlgorithm(256));
    }
    
    // example 3
    {
        vigra::IImage labeling(w, h);
        
        .. // get seeds from somewhere, e.g. an interactive labeling program,
           // make sure that label 1 corresponds to the background
        
        // bias the watershed algorithm so that the background is preferred
        // by reducing the cost for label 1 to 90%
        watershedsRegionGrowing(srcImageRange(gradMag), destImage(labeling),
                                WatershedOptions().biasLabel(1, 0.9));
    }

Required Interface:

    SrcIterator src_upperleft, src_lowerright;
    DestIterator dest_upperleft;

    SrcAccessor src_accessor;
    DestAccessor dest_accessor;

    // compare src values
    src_accessor(src_upperleft) <= src_accessor(src_upperleft)

    // set result
    int label;
    dest_accessor.set(label, dest_upperleft);
unsigned int vigra::generateWatershedSeeds3D (   ...  ) 

Generate seeds for watershed computation and seeded region growing.

The source image is a boundary indicator such as the gradient magnitude or the trace of the boundaryTensor(). Seeds are generally generated at locations where the boundaryness (i.e. the likelihood of the point being on the boundary) is very small. In particular, seeds can be placed by either looking for local minima (possibly including minimal plateaus) of the boundaryness, of by looking at level sets (i.e. regions where the boundaryness is below a threshold). Both methods can also be combined, so that only minima below a threshold are returned. The particular seeding strategy is specified by the options object (see SeedOptions).

The pixel type of the input image must be LessThanComparable. The pixel type of the output image must be large enough to hold the labels for all seeds. (typically, you will use UInt32). The function will label seeds by consecutive integers (starting from 1) and returns the largest label it used.

Pass vigra::EightNeighborCode or vigra::FourNeighborCode to determine the neighborhood where pixel values are compared.

The function uses accessors.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        generateWatershedSeeds(SrcIterator upperlefts, SrcIterator lowerrights, SrcAccessor sa,
                               DestIterator upperleftd, DestAccessor da, 
                               Neighborhood neighborhood = EightNeighborCode(),
                               SeedOptions const & options = SeedOptions());
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,
                  class DestIterator, class DestAccessor,
                  class Neighborhood = EightNeighborCode>
        unsigned int
        generateWatershedSeeds(triple<SrcIterator, SrcIterator, SrcAccessor> src,
                               pair<DestIterator, DestAccessor> dest, 
                               Neighborhood neighborhood = EightNeighborCode(),
                               SeedOptions const & options = SeedOptions());
    }

Usage:

#include <vigra/watersheds.hxx>
Namespace: vigra

For detailed examples see watershedsRegionGrowing().

unsigned int vigra::watersheds3D (   ...  ) 

Region Segmentation by means of the watershed algorithm.

Declarations:

pass arguments explicitly:

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,class SrcShape,
                  class DestIterator, class DestAccessor,
                  class Neighborhood3D>
        unsigned int watersheds3D(SrcIterator s_Iter, SrcShape srcShape, SrcAccessor sa,
                                  DestIterator d_Iter, DestAccessor da,
                                  Neighborhood3D neighborhood3D);
    }

use argument objects in conjunction with Argument Object Factories :

    namespace vigra {
        template <class SrcIterator, class SrcAccessor,class SrcShape,
                  class DestIterator, class DestAccessor,
                  class Neighborhood3D>
        unsigned int watersheds3D(triple<SrcIterator, SrcShape, SrcAccessor> src,
                                  pair<DestIterator, DestAccessor> dest,
                                  Neighborhood3D neighborhood3D);
    }

use with 3D-Six-Neighborhood:

    namespace vigra {    
    
        template <class SrcIterator, class SrcAccessor,class SrcShape,
                  class DestIterator, class DestAccessor>
        unsigned int watersheds3DSix(triple<SrcIterator, SrcShape, SrcAccessor> src,
                                     pair<DestIterator, DestAccessor> dest);
                                    
    }

use with 3D-TwentySix-Neighborhood:

    namespace vigra {    
    
        template <class SrcIterator, class SrcAccessor,class SrcShape,
                  class DestIterator, class DestAccessor>
        unsigned int watersheds3DTwentySix(triple<SrcIterator, SrcShape, SrcAccessor> src,
                                           pair<DestIterator, DestAccessor> dest);
                                    
    }

This function implements the union-find version of the watershed algorithms as described in

J. Roerdink, R. Meijster: "<em>The watershed transform: definitions, algorithms, and parallelization strategies</em>", Fundamenta Informaticae, 41:187-228, 2000

The source volume is a boundary indicator such as the gradient magnitude of the trace of the boundaryTensor(). Local minima of the boundary indicator are used as region seeds, and all other voxels are recursively assigned to the same region as their lowest neighbor. Pass vigra::NeighborCode3DSix or vigra::NeighborCode3DTwentySix to determine the neighborhood where voxel values are compared. The voxel type of the input volume must be LessThanComparable. The function uses accessors.

...probably soon in VIGRA: Note that VIGRA provides an alternative implementation of the watershed transform via seededRegionGrowing3D(). It is slower, but handles plateaus better and allows to keep a one pixel wide boundary between regions.

Usage:

#include <vigra/watersheds3D.hxx>
Namespace: vigra

Example: watersheds3D of the gradient magnitude.

    typedef vigra::MultiArray<3,int> IntVolume;
    typedef vigra::MultiArray<3,double> DVolume;
    DVolume src(DVolume::difference_type(w,h,d));
    IntVolume dest(IntVolume::difference_type(w,h,d));

    float gauss=1;

    vigra::MultiArray<3, vigra::TinyVector<float,3> > temp(IntVolume::difference_type(w,h,d));
    vigra::gaussianGradientMultiArray(srcMultiArrayRange(vol),destMultiArray(temp),gauss);

    IntVolume::iterator temp_iter=temp.begin();
    for(DVolume::iterator iter=src.begin(); iter!=src.end(); ++iter, ++temp_iter)
        *iter = norm(*temp_iter);
    
    // find 6-connected regions
    int max_region_label = vigra::watersheds3DSix(srcMultiArrayRange(src), destMultiArray(dest));

    // find 26-connected regions
    max_region_label = vigra::watersheds3DTwentySix(srcMultiArrayRange(src), destMultiArray(dest));

Required Interface:

    SrcIterator src_begin;
    SrcShape src_shape;
    DestIterator dest_begin;

    SrcAccessor src_accessor;
    DestAccessor dest_accessor;
    
    // compare src values
    src_accessor(src_begin) <= src_accessor(src_begin)

    // set result
    int label;
    dest_accessor.set(label, dest_begin);

© Ullrich Köthe (ullrich.koethe@iwr.uni-heidelberg.de)
Heidelberg Collaboratory for Image Processing, University of Heidelberg, Germany

html generated using doxygen and Python
vigra 1.8.0 (20 Sep 2011)