OpenCV  4.10.0
Open Source Computer Vision
Loading...
Searching...
No Matches
Public Member Functions | List of all members
cv::ximgproc::StructuredEdgeDetection Class Referenceabstract

Class implementing edge detection algorithm from [70] : More...

#include <opencv2/ximgproc/structured_edge_detection.hpp>

Collaboration diagram for cv::ximgproc::StructuredEdgeDetection:

Public Member Functions

virtual void computeOrientation (cv::InputArray src, cv::OutputArray dst) const =0
 The function computes orientation from edge image.
 
virtual void detectEdges (cv::InputArray src, cv::OutputArray dst) const =0
 The function detects edges in src and draw them to dst.
 
virtual void edgesNms (cv::InputArray edge_image, cv::InputArray orientation_image, cv::OutputArray dst, int r=2, int s=0, float m=1, bool isParallel=true) const =0
 The function edgenms in edge image and suppress edges where edge is stronger in orthogonal direction.
 
- 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
 
void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage.
 
void write (FileStorage &fs, const String &name) const
 

Additional Inherited Members

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

Detailed Description

Class implementing edge detection algorithm from [70] :

Member Function Documentation

◆ computeOrientation()

virtual void cv::ximgproc::StructuredEdgeDetection::computeOrientation ( cv::InputArray  src,
cv::OutputArray  dst 
) const
pure virtual
Python:
cv.ximgproc.StructuredEdgeDetection.computeOrientation(src[, dst]) -> dst

The function computes orientation from edge image.

Parameters
srcedge image.
dstorientation image.

◆ detectEdges()

virtual void cv::ximgproc::StructuredEdgeDetection::detectEdges ( cv::InputArray  src,
cv::OutputArray  dst 
) const
pure virtual
Python:
cv.ximgproc.StructuredEdgeDetection.detectEdges(src[, dst]) -> dst

The function detects edges in src and draw them to dst.

The algorithm underlies this function is much more robust to texture presence, than common approaches, e.g. Sobel

Parameters
srcsource image (RGB, float, in [0;1]) to detect edges
dstdestination image (grayscale, float, in [0;1]) where edges are drawn
See also
Sobel, Canny

◆ edgesNms()

virtual void cv::ximgproc::StructuredEdgeDetection::edgesNms ( cv::InputArray  edge_image,
cv::InputArray  orientation_image,
cv::OutputArray  dst,
int  r = 2,
int  s = 0,
float  m = 1,
bool  isParallel = true 
) const
pure virtual
Python:
cv.ximgproc.StructuredEdgeDetection.edgesNms(edge_image, orientation_image[, dst[, r[, s[, m[, isParallel]]]]]) -> dst

The function edgenms in edge image and suppress edges where edge is stronger in orthogonal direction.

Parameters
edge_imageedge image from detectEdges function.
orientation_imageorientation image from computeOrientation function.
dstsuppressed image (grayscale, float, in [0;1])
rradius for NMS suppression.
sradius for boundary suppression.
mmultiplier for conservative suppression.
isParallelenables/disables parallel computing.

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