OpenCV
3.2.0
Open Source Computer Vision
|
The ERStat structure represents a class-specific Extremal Region (ER). More...
#include "erfilter.hpp"
Public Member Functions | |
ERStat (int level=256, int pixel=0, int x=0, int y=0) | |
Constructor. More... | |
~ERStat () | |
Destructor. More... | |
Public Attributes | |
int | area |
incrementally computable features More... | |
double | central_moments [3] |
order 2 central moments to construct the covariance matrix More... | |
ERStat * | child |
float | convex_hull_ratio |
Ptr< std::deque< int > > | crossings |
horizontal crossings More... | |
int | euler |
euler number More... | |
float | hole_area_ratio |
2nd stage features More... | |
int | level |
bool | local_maxima |
wenever the regions is a local maxima of the probability More... | |
ERStat * | max_probability_ancestor |
float | med_crossings |
median of the crossings at three different height levels More... | |
ERStat * | min_probability_ancestor |
ERStat * | next |
float | num_inflexion_points |
ERStat * | parent |
pointers preserving the tree structure of the component tree More... | |
int | perimeter |
int | pixel |
seed point and the threshold (max grey-level value) More... | |
std::vector< int > * | pixels |
ERStat * | prev |
double | probability |
probability that the ER belongs to the class we are looking for More... | |
double | raw_moments [2] |
order 1 raw moments to derive the centroid More... | |
Rect | rect |
The ERStat structure represents a class-specific Extremal Region (ER).
An ER is a 4-connected set of pixels with all its grey-level values smaller than the values in its outer boundary. A class-specific ER is selected (using a classifier) from all the ER's in the component tree of the image. :
|
explicit |
Constructor.
cv::text::ERStat::~ERStat | ( | ) |
Destructor.
int cv::text::ERStat::area |
incrementally computable features
double cv::text::ERStat::central_moments[3] |
order 2 central moments to construct the covariance matrix
ERStat* cv::text::ERStat::child |
float cv::text::ERStat::convex_hull_ratio |
Ptr<std::deque<int> > cv::text::ERStat::crossings |
horizontal crossings
int cv::text::ERStat::euler |
euler number
float cv::text::ERStat::hole_area_ratio |
2nd stage features
int cv::text::ERStat::level |
bool cv::text::ERStat::local_maxima |
wenever the regions is a local maxima of the probability
ERStat* cv::text::ERStat::max_probability_ancestor |
float cv::text::ERStat::med_crossings |
median of the crossings at three different height levels
ERStat* cv::text::ERStat::min_probability_ancestor |
ERStat* cv::text::ERStat::next |
float cv::text::ERStat::num_inflexion_points |
ERStat* cv::text::ERStat::parent |
pointers preserving the tree structure of the component tree
int cv::text::ERStat::perimeter |
int cv::text::ERStat::pixel |
seed point and the threshold (max grey-level value)
std::vector<int>* cv::text::ERStat::pixels |
ERStat* cv::text::ERStat::prev |
double cv::text::ERStat::probability |
probability that the ER belongs to the class we are looking for
double cv::text::ERStat::raw_moments[2] |
order 1 raw moments to derive the centroid
Rect cv::text::ERStat::rect |