CGAL::Classification::Feature::Eigentropy Class Reference

#include <CGAL/Classification/Feature/Eigen.h>

Inherits from

CGAL::Classification::Feature_base.

Definition

Feature based on the eigenvalues of the covariance matrix of a local neighborhood.

Eigentropy is defined, for the 3 eigenvalues \(\lambda_1 \ge \lambda_2 \ge \lambda_3 \ge 0\), as:

\[ - \sum_{i=1}^3 \lambda_i \times \log{\lambda_i} \]

Its default name is "eigentropy".

Public Member Functions
template<typename InputRange >
	Eigentropy (const InputRange &input, const Local_eigen_analysis &eigen)
	Constructs the feature. More...
Public Member Functions inherited from CGAL::Classification::Feature_base
const std::string &	name () const
	Returns the name of the feature (initialized to abstract_feature for Feature_base).
void	set_name (const std::string &name)
	Changes the name of the feature.
virtual float	value (std::size_t index)=0
	Returns the value taken by the feature for at the item for the item at position index. More...

Constructor & Destructor Documentation

Eigentropy()

template<typename InputRange >

CGAL::Classification::Feature::Eigentropy::Eigentropy	(	const InputRange &	input,
		const Local_eigen_analysis &	eigen
	)

Constructs the feature.

Parameters

input	point range.
eigen	class with precomputed eigenvectors and eigenvalues.