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

Strategie for the selective search segmentation algorithm The class implements a generic stragery for the algorithm described in. More...

#include <opencv2/ximgproc/segmentation.hpp>

Inheritance diagram for cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategy:
cv::Algorithm cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategyColor cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategyFill cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategyMultiple cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategySize cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategyTexture

Public Member Functions

virtual float get (int r1, int r2)=0
 Return the score between two regions (between 0 and 1)
 
virtual void merge (int r1, int r2)=0
 Inform the strategy that two regions will be merged.
 
virtual void setImage (InputArray img, InputArray regions, InputArray sizes, int image_id=-1)=0
 Set a initial image, with a segementation.
 
- 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

Strategie for the selective search segmentation algorithm The class implements a generic stragery for the algorithm described in.

uijlings2013selective.

Member Function Documentation

virtual float cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategy::get ( int  r1,
int  r2 
)
pure virtual
Python:
retval=cv.ximgproc_segmentation_SelectiveSearchSegmentationStrategy.get(r1, r2)

Return the score between two regions (between 0 and 1)

Parameters
r1The first region
r2The second region
virtual void cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategy::merge ( int  r1,
int  r2 
)
pure virtual
Python:
None=cv.ximgproc_segmentation_SelectiveSearchSegmentationStrategy.merge(r1, r2)

Inform the strategy that two regions will be merged.

Parameters
r1The first region
r2The second region
virtual void cv::ximgproc::segmentation::SelectiveSearchSegmentationStrategy::setImage ( InputArray  img,
InputArray  regions,
InputArray  sizes,
int  image_id = -1 
)
pure virtual
Python:
None=cv.ximgproc_segmentation_SelectiveSearchSegmentationStrategy.setImage(img, regions, sizes[, image_id])

Set a initial image, with a segementation.

Parameters
imgThe input image. Any number of channel can be provided
regionsA segementation of the image. The parameter must be the same size of img.
sizesThe sizes of different regions
image_idIf not set to -1, try to cache pre-computations. If the same set og (img, regions, size) is used, the image_id need to be the same.

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