ITK  5.0.0
Insight Segmentation and Registration Toolkit
Module ITKWatersheds
+ Collaboration diagram for Module ITKWatersheds:


class  itk::watershed::Boundary< TScalar, TDimension >
class  itk::watershed::BoundaryResolver< TPixelType, TDimension >
class  itk::watershed::EquivalenceRelabeler< TScalar, TImageDimension >
class  itk::IsolatedWatershedImageFilter< TInputImage, TOutputImage >
class  itk::MorphologicalWatershedFromMarkersImageFilter< TInputImage, TLabelImage >
class  itk::MorphologicalWatershedImageFilter< TInputImage, TOutputImage >
class  itk::OneWayEquivalencyTable
class  itk::watershed::Relabeler< TScalar, TImageDimension >
class  itk::watershed::Segmenter< TInputImage >
class  itk::watershed::SegmentTable< TScalar >
class  itk::watershed::SegmentTree< TScalar >
class  itk::watershed::SegmentTreeGenerator< TScalar >
class  itk::TobogganImageFilter< TInputImage, TOutputImage >
class  itk::WatershedImageFilter< TInputImage >
class  itk::WatershedMiniPipelineProgressCommand

Detailed Description

This module contains classes related to watershed segmentation. The watershed algorithm proceeds in several steps. First, an initial classification of all points into catchment basin regions is done by tracing each point down its path of steepest descent to a local minima. Next, neighboring regions and the boundaries between them are analyzed according to some saliency measure (such as minimum boundary height) to produce a tree of merges among adjacent regions. These merges occur at different maximum saliency values. Finally, a label images are generated from the merge tree.

This module also contains classes related to marker-based watershed segmentation. For more information, see the Insight Journal article:

Beare, R. and Lehmann, G. "The watershed transform in ITK - discussion and new developments." The Insight Journal - 2006 January - June.