OpenCV  4.1.0-dev
Open Source Computer Vision
Public Member Functions | List of all members
cv::ximgproc::ContourFitting Class Reference

Class for ContourFitting algorithms. ContourFitting match two contours \( z_a \) and \( z_b \) minimizing distance

\[ d(z_a,z_b)=\sum (a_n - s b_n e^{j(n \alpha +\phi )})^2 \]

where \( a_n \) and \( b_n \) are Fourier descriptors of \( z_a \) and \( z_b \) and s is a scaling factor and \( \phi \) is angle rotation and \( \alpha \) is starting point factor adjustement. More...

#include <opencv2/ximgproc/fourier_descriptors.hpp>

Inheritance diagram for cv::ximgproc::ContourFitting:
cv::Algorithm

Public Member Functions

 ContourFitting (int ctr=1024, int fd=16)
 Fit two closed curves using fourier descriptors. More details in [175] and [16]. More...
 
void estimateTransformation (InputArray src, InputArray dst, OutputArray alphaPhiST, double *dist=0, bool fdContour=false)
 Fit two closed curves using fourier descriptors. More details in [175] and [16]. More...
 
void estimateTransformation (InputArray src, InputArray dst, OutputArray alphaPhiST, double &dist, bool fdContour=false)
 Fit two closed curves using fourier descriptors. More details in [175] and [16]. More...
 
int getCtrSize ()
 
int getFDSize ()
 
void setCtrSize (int n)
 set number of Fourier descriptors used in estimateTransformation More...
 
void setFDSize (int n)
 set number of Fourier descriptors when estimateTransformation used vector<Point> More...
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state. More...
 
virtual bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
 
virtual String getDefaultName () const
 
virtual void read (const FileNode &fn)
 Reads algorithm parameters from a file storage. More...
 
virtual void save (const String &filename) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage. More...
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 simplified API for language bindings This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...
 

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

Detailed Description

Class for ContourFitting algorithms. ContourFitting match two contours \( z_a \) and \( z_b \) minimizing distance

\[ d(z_a,z_b)=\sum (a_n - s b_n e^{j(n \alpha +\phi )})^2 \]

where \( a_n \) and \( b_n \) are Fourier descriptors of \( z_a \) and \( z_b \) and s is a scaling factor and \( \phi \) is angle rotation and \( \alpha \) is starting point factor adjustement.

Constructor & Destructor Documentation

§ ContourFitting()

cv::ximgproc::ContourFitting::ContourFitting ( int  ctr = 1024,
int  fd = 16 
)
inline

Fit two closed curves using fourier descriptors. More details in [175] and [16].

Parameters
ctrnumber of Fourier descriptors equal to number of contour points after resampling.
fdContour defining second shape (Target).

Member Function Documentation

§ estimateTransformation() [1/2]

void cv::ximgproc::ContourFitting::estimateTransformation ( InputArray  src,
InputArray  dst,
OutputArray  alphaPhiST,
double *  dist = 0,
bool  fdContour = false 
)
Python:
alphaPhiST, dist=cv.ximgproc_ContourFitting.estimateTransformation(src, dst[, alphaPhiST[, fdContour]])

Fit two closed curves using fourier descriptors. More details in [175] and [16].

Parameters
srcContour defining first shape.
dstContour defining second shape (Target).
alphaPhiST: \( \alpha \)=alphaPhiST(0,0), \( \phi \)=alphaPhiST(0,1) (in radian), s=alphaPhiST(0,2), Tx=alphaPhiST(0,3), Ty=alphaPhiST(0,4) rotation center
distdistance between src and dst after matching.
fdContourfalse then src and dst are contours and true src and dst are fourier descriptors.

§ estimateTransformation() [2/2]

void cv::ximgproc::ContourFitting::estimateTransformation ( InputArray  src,
InputArray  dst,
OutputArray  alphaPhiST,
double &  dist,
bool  fdContour = false 
)
Python:
alphaPhiST, dist=cv.ximgproc_ContourFitting.estimateTransformation(src, dst[, alphaPhiST[, fdContour]])

Fit two closed curves using fourier descriptors. More details in [175] and [16].

Parameters
srcContour defining first shape.
dstContour defining second shape (Target).
alphaPhiST: \( \alpha \)=alphaPhiST(0,0), \( \phi \)=alphaPhiST(0,1) (in radian), s=alphaPhiST(0,2), Tx=alphaPhiST(0,3), Ty=alphaPhiST(0,4) rotation center
distdistance between src and dst after matching.
fdContourfalse then src and dst are contours and true src and dst are fourier descriptors.

§ getCtrSize()

int cv::ximgproc::ContourFitting::getCtrSize ( )
inline
Python:
retval=cv.ximgproc_ContourFitting.getCtrSize()
Returns
number of fourier descriptors

§ getFDSize()

int cv::ximgproc::ContourFitting::getFDSize ( )
inline
Python:
retval=cv.ximgproc_ContourFitting.getFDSize()
Returns
number of fourier descriptors used for optimal curve matching

§ setCtrSize()

void cv::ximgproc::ContourFitting::setCtrSize ( int  n)
Python:
None=cv.ximgproc_ContourFitting.setCtrSize(n)

set number of Fourier descriptors used in estimateTransformation

Parameters
nnumber of Fourier descriptors equal to number of contour points after resampling.

§ setFDSize()

void cv::ximgproc::ContourFitting::setFDSize ( int  n)
Python:
None=cv.ximgproc_ContourFitting.setFDSize(n)

set number of Fourier descriptors when estimateTransformation used vector<Point>

Parameters
nnumber of fourier descriptors used for optimal curve matching.

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