OpenCV  4.1.0
Open Source Computer Vision
Public Member Functions | List of all members
cv::ShapeContextDistanceExtractor Class Referenceabstract

Implementation of the Shape Context descriptor and matching algorithm. More...

#include <opencv2/shape/shape_distance.hpp>

Inheritance diagram for cv::ShapeContextDistanceExtractor:
cv::ShapeDistanceExtractor cv::Algorithm

Public Member Functions

virtual int getAngularBins () const =0
 
virtual float getBendingEnergyWeight () const =0
 
virtual Ptr
< HistogramCostExtractor
getCostExtractor () const =0
 
virtual float getImageAppearanceWeight () const =0
 
virtual void getImages (OutputArray image1, OutputArray image2) const =0
 
virtual float getInnerRadius () const =0
 
virtual int getIterations () const =0
 
virtual float getOuterRadius () const =0
 
virtual int getRadialBins () const =0
 
virtual bool getRotationInvariant () const =0
 
virtual float getShapeContextWeight () const =0
 
virtual float getStdDev () const =0
 
virtual Ptr< ShapeTransformergetTransformAlgorithm () const =0
 
virtual void setAngularBins (int nAngularBins)=0
 Establish the number of angular bins for the Shape Context Descriptor used in the shape matching pipeline.
 
virtual void setBendingEnergyWeight (float bendingEnergyWeight)=0
 Set the weight of the Bending Energy in the final value of the shape distance. The bending energy definition depends on what transformation is being used to align the shapes. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy.
 
virtual void setCostExtractor (Ptr< HistogramCostExtractor > comparer)=0
 Set the algorithm used for building the shape context descriptor cost matrix.
 
virtual void setImageAppearanceWeight (float imageAppearanceWeight)=0
 Set the weight of the Image Appearance cost in the final value of the shape distance. The image appearance cost is defined as the sum of squared brightness differences in Gaussian windows around corresponding image points. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy. If this value is set to a number different from 0, is mandatory to set the images that correspond to each shape.
 
virtual void setImages (InputArray image1, InputArray image2)=0
 Set the images that correspond to each shape. This images are used in the calculation of the Image Appearance cost.
 
virtual void setInnerRadius (float innerRadius)=0
 Set the inner radius of the shape context descriptor.
 
virtual void setIterations (int iterations)=0
 
virtual void setOuterRadius (float outerRadius)=0
 Set the outer radius of the shape context descriptor.
 
virtual void setRadialBins (int nRadialBins)=0
 Establish the number of radial bins for the Shape Context Descriptor used in the shape matching pipeline.
 
virtual void setRotationInvariant (bool rotationInvariant)=0
 
virtual void setShapeContextWeight (float shapeContextWeight)=0
 Set the weight of the shape context distance in the final value of the shape distance. The shape context distance between two shapes is defined as the symmetric sum of shape context matching costs over best matching points. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy.
 
virtual void setStdDev (float sigma)=0
 Set the value of the standard deviation for the Gaussian window for the image appearance cost.
 
virtual void setTransformAlgorithm (Ptr< ShapeTransformer > transformer)=0
 Set the algorithm used for aligning the shapes.
 
- Public Member Functions inherited from cv::ShapeDistanceExtractor
virtual float computeDistance (InputArray contour1, InputArray contour2)=0
 Compute the shape distance between two shapes defined by its contours.
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state.
 
virtual bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.
 
virtual String getDefaultName () const
 
virtual void read (const FileNode &fn)
 Reads algorithm parameters from a file storage.
 
virtual void save (const String &filename) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage.
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 simplified API for language bindingsThis is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
 

Additional Inherited Members

- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp > load (const String &filename, const String &objname=String())
 Loads algorithm from the file.
 
template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String.
 
template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
 Reads algorithm from the file node.
 
- Protected Member Functions inherited from cv::Algorithm
void writeFormat (FileStorage &fs) const
 

Detailed Description

Implementation of the Shape Context descriptor and matching algorithm.

proposed by Belongie et al. in "Shape Matching and Object Recognition Using Shape Contexts" (PAMI 2002). This implementation is packaged in a generic scheme, in order to allow you the implementation of the common variations of the original pipeline.

Member Function Documentation

virtual int cv::ShapeContextDistanceExtractor::getAngularBins ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getAngularBins()
virtual float cv::ShapeContextDistanceExtractor::getBendingEnergyWeight ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getBendingEnergyWeight()
virtual Ptr<HistogramCostExtractor> cv::ShapeContextDistanceExtractor::getCostExtractor ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getCostExtractor()
virtual float cv::ShapeContextDistanceExtractor::getImageAppearanceWeight ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getImageAppearanceWeight()
virtual void cv::ShapeContextDistanceExtractor::getImages ( OutputArray  image1,
OutputArray  image2 
) const
pure virtual
Python:
image1, image2=cv.ShapeContextDistanceExtractor.getImages([, image1[, image2]])
virtual float cv::ShapeContextDistanceExtractor::getInnerRadius ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getInnerRadius()
virtual int cv::ShapeContextDistanceExtractor::getIterations ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getIterations()
virtual float cv::ShapeContextDistanceExtractor::getOuterRadius ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getOuterRadius()
virtual int cv::ShapeContextDistanceExtractor::getRadialBins ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getRadialBins()
virtual bool cv::ShapeContextDistanceExtractor::getRotationInvariant ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getRotationInvariant()
virtual float cv::ShapeContextDistanceExtractor::getShapeContextWeight ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getShapeContextWeight()
virtual float cv::ShapeContextDistanceExtractor::getStdDev ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getStdDev()
virtual Ptr<ShapeTransformer> cv::ShapeContextDistanceExtractor::getTransformAlgorithm ( ) const
pure virtual
Python:
retval=cv.ShapeContextDistanceExtractor.getTransformAlgorithm()
virtual void cv::ShapeContextDistanceExtractor::setAngularBins ( int  nAngularBins)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setAngularBins(nAngularBins)

Establish the number of angular bins for the Shape Context Descriptor used in the shape matching pipeline.

Parameters
nAngularBinsThe number of angular bins in the shape context descriptor.
virtual void cv::ShapeContextDistanceExtractor::setBendingEnergyWeight ( float  bendingEnergyWeight)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setBendingEnergyWeight(bendingEnergyWeight)

Set the weight of the Bending Energy in the final value of the shape distance. The bending energy definition depends on what transformation is being used to align the shapes. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy.

Parameters
bendingEnergyWeightThe weight of the Bending Energy in the final distance value.
virtual void cv::ShapeContextDistanceExtractor::setCostExtractor ( Ptr< HistogramCostExtractor comparer)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setCostExtractor(comparer)

Set the algorithm used for building the shape context descriptor cost matrix.

Parameters
comparerSmart pointer to a HistogramCostExtractor, an algorithm that defines the cost matrix between descriptors.
virtual void cv::ShapeContextDistanceExtractor::setImageAppearanceWeight ( float  imageAppearanceWeight)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setImageAppearanceWeight(imageAppearanceWeight)

Set the weight of the Image Appearance cost in the final value of the shape distance. The image appearance cost is defined as the sum of squared brightness differences in Gaussian windows around corresponding image points. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy. If this value is set to a number different from 0, is mandatory to set the images that correspond to each shape.

Parameters
imageAppearanceWeightThe weight of the appearance cost in the final distance value.
virtual void cv::ShapeContextDistanceExtractor::setImages ( InputArray  image1,
InputArray  image2 
)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setImages(image1, image2)

Set the images that correspond to each shape. This images are used in the calculation of the Image Appearance cost.

Parameters
image1Image corresponding to the shape defined by contours1.
image2Image corresponding to the shape defined by contours2.
virtual void cv::ShapeContextDistanceExtractor::setInnerRadius ( float  innerRadius)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setInnerRadius(innerRadius)

Set the inner radius of the shape context descriptor.

Parameters
innerRadiusThe value of the inner radius.
virtual void cv::ShapeContextDistanceExtractor::setIterations ( int  iterations)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setIterations(iterations)
virtual void cv::ShapeContextDistanceExtractor::setOuterRadius ( float  outerRadius)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setOuterRadius(outerRadius)

Set the outer radius of the shape context descriptor.

Parameters
outerRadiusThe value of the outer radius.
virtual void cv::ShapeContextDistanceExtractor::setRadialBins ( int  nRadialBins)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setRadialBins(nRadialBins)

Establish the number of radial bins for the Shape Context Descriptor used in the shape matching pipeline.

Parameters
nRadialBinsThe number of radial bins in the shape context descriptor.
virtual void cv::ShapeContextDistanceExtractor::setRotationInvariant ( bool  rotationInvariant)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setRotationInvariant(rotationInvariant)
virtual void cv::ShapeContextDistanceExtractor::setShapeContextWeight ( float  shapeContextWeight)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setShapeContextWeight(shapeContextWeight)

Set the weight of the shape context distance in the final value of the shape distance. The shape context distance between two shapes is defined as the symmetric sum of shape context matching costs over best matching points. The final value of the shape distance is a user-defined linear combination of the shape context distance, an image appearance distance, and a bending energy.

Parameters
shapeContextWeightThe weight of the shape context distance in the final distance value.
virtual void cv::ShapeContextDistanceExtractor::setStdDev ( float  sigma)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setStdDev(sigma)

Set the value of the standard deviation for the Gaussian window for the image appearance cost.

Parameters
sigmaStandard Deviation.
virtual void cv::ShapeContextDistanceExtractor::setTransformAlgorithm ( Ptr< ShapeTransformer transformer)
pure virtual
Python:
None=cv.ShapeContextDistanceExtractor.setTransformAlgorithm(transformer)

Set the algorithm used for aligning the shapes.

Parameters
transformerSmart pointer to a ShapeTransformer, an algorithm that defines the aligning transformation.

The documentation for this class was generated from the following file: