Structured forests for fast edge detection#

Detailed Description#

This module contains implementations of modern structured edge detection algorithms, i.e. algorithms which somehow takes into account pixel affinities in natural images.

Classes#

Name

Description

class cv::ximgproc::RFFeatureGetter

View details

class cv::ximgproc::StructuredEdgeDetection

Class implementing edge detection algorithm from [81] : View details

Function Documentation#

createRFFeatureGetter()#

Ptr< RFFeatureGetter > cv::ximgproc::createRFFeatureGetter()

#include <opencv2/ximgproc/structured_edge_detection.hpp>

createStructuredEdgeDetection()#

Ptr< StructuredEdgeDetection > cv::ximgproc::createStructuredEdgeDetection(
const String & model,
Ptr< const RFFeatureGetter > howToGetFeatures = Ptr< RFFeatureGetter >() )

#include <opencv2/ximgproc/structured_edge_detection.hpp>

The only constructor

Parameters

  • model — : name of the file where the model is stored

  • howToGetFeatures — : optional object inheriting from RFFeatureGetter. You need it only if you would like to train your own forest, pass NULL otherwise