Base for classes to build clsfy_classifier_1d objects. More...

#include <clsfy_mean_square_1d_builder.h>

Inheritance diagram for clsfy_mean_square_1d_builder:

Public Member Functions
	clsfy_mean_square_1d_builder ()
virtual	~clsfy_mean_square_1d_builder ()
virtual clsfy_classifier_1d *	new_classifier () const
	Create empty model.
virtual double	build (clsfy_classifier_1d &classifier, const vnl_vector< double > &egs, const vnl_vector< double > &wts, const vcl_vector< unsigned > &outputs) const
	Build a binary_threshold classifier.
virtual double	build (clsfy_classifier_1d &classifier, vnl_vector< double > &egs0, vnl_vector< double > &wts0, vnl_vector< double > &egs1, vnl_vector< double > &wts1) const
	Build a mean_square classifier.
virtual double	build_from_sorted_data (clsfy_classifier_1d &classifier, const vbl_triple< double, int, int > *data, const vnl_vector< double > &wts) const
	Train classifier, returning weighted error.
virtual vcl_string	is_a () const
	Name of the class.
virtual bool	is_class (vcl_string const &s) const
	Name of the class.
short	version_no () const
	Version number for I/O.
virtual clsfy_builder_1d *	clone () const
	Create a copy on the heap and return base class pointer.
virtual void	print_summary (vcl_ostream &os) const
	Print class to os.
virtual void	b_write (vsl_b_ostream &bfs) const
	Save class to binary file stream.
virtual void	b_read (vsl_b_istream &bfs)
	Load class from binary file stream.
virtual void	config (vcl_istream &as)
	Initialise the parameters from a text stream.
Static Public Member Functions
static vcl_auto_ptr < clsfy_builder_1d >	new_builder (vcl_istream &as)
	Load description from a text stream.

Detailed Description

Base for classes to build clsfy_classifier_1d objects.

Definition at line 17 of file clsfy_mean_square_1d_builder.h.

Constructor & Destructor Documentation

clsfy_mean_square_1d_builder::clsfy_mean_square_1d_builder ( )

Definition at line 21 of file clsfy_mean_square_1d_builder.cxx.

clsfy_mean_square_1d_builder::~clsfy_mean_square_1d_builder ( ) [virtual]

Definition at line 27 of file clsfy_mean_square_1d_builder.cxx.

Member Function Documentation

void clsfy_mean_square_1d_builder::b_read ( vsl_b_istream & bfs ) [virtual]

Load class from binary file stream.

Implements clsfy_builder_1d.

Definition at line 362 of file clsfy_mean_square_1d_builder.cxx.

void clsfy_mean_square_1d_builder::b_write ( vsl_b_ostream & bfs ) const [virtual]

Save class to binary file stream.

Implements clsfy_builder_1d.

Definition at line 351 of file clsfy_mean_square_1d_builder.cxx.

double clsfy_mean_square_1d_builder::build	(	clsfy_classifier_1d &	classifier,
		const vnl_vector< double > &	egs,
		const vnl_vector< double > &	wts,
		const vcl_vector< unsigned > &	outputs
	)		const `[virtual]`

Build a binary_threshold classifier.

Train classifier, returning weighted error Selects parameters of classifier which best separate examples from two classes, weighting examples appropriately when estimating the misclassification rate. Returns weighted sum of error, e.wts, where e_i =0 for correct classifications, e_i=1 for incorrect.

Implements clsfy_builder_1d.

Definition at line 53 of file clsfy_mean_square_1d_builder.cxx.

double clsfy_mean_square_1d_builder::build	(	clsfy_classifier_1d &	classifier,
		vnl_vector< double > &	egs0,
		vnl_vector< double > &	wts0,
		vnl_vector< double > &	egs1,
		vnl_vector< double > &	wts1
	)		const `[virtual]`

Build a mean_square classifier.

Train classifier, returning weighted error Selects parameters of classifier which best separate examples from two classes, weighting examples appropriately when estimating the misclassification rate. Returns weighted sum of error, e.wts, where e_i =0 for correct classifications, e_i=1 for incorrect.

nb here egs0 are -ve examples and egs1 are +ve examples

Implements clsfy_builder_1d.

Definition at line 161 of file clsfy_mean_square_1d_builder.cxx.

double clsfy_mean_square_1d_builder::build_from_sorted_data	(	clsfy_classifier_1d &	classifier,
		const vbl_triple< double, int, int > *	data,
		const vnl_vector< double > &	wts
	)		const `[virtual]`

Train classifier, returning weighted error.

Selects parameters of classifier which best separate examples, weighting examples appropriately when estimating the misclassification rate. data[i] is a triple, {value,class_number,weight} Returns weighted sum of error. Note that input "data" must be sorted to use this routine

Assumes two classes

Implements clsfy_builder_1d.

Definition at line 270 of file clsfy_mean_square_1d_builder.cxx.

clsfy_builder_1d * clsfy_mean_square_1d_builder::clone ( ) const [virtual]

Create a copy on the heap and return base class pointer.

Implements clsfy_builder_1d.

Definition at line 332 of file clsfy_mean_square_1d_builder.cxx.

void clsfy_builder_1d::config ( vcl_istream & as ) [virtual, inherited]

Initialise the parameters from a text stream.

Default case accepts no parameters.

Definition at line 37 of file clsfy_builder_1d.cxx.

vcl_string clsfy_mean_square_1d_builder::is_a ( ) const [virtual]

Name of the class.

Reimplemented from clsfy_builder_1d.

Definition at line 286 of file clsfy_mean_square_1d_builder.cxx.

bool clsfy_mean_square_1d_builder::is_class ( vcl_string const & s ) const [virtual]

Name of the class.

Reimplemented from clsfy_builder_1d.

Definition at line 291 of file clsfy_mean_square_1d_builder.cxx.

vcl_auto_ptr< clsfy_builder_1d > clsfy_builder_1d::new_builder ( vcl_istream & as ) [static, inherited]

Load description from a text stream.

The stream should contain the name of the feature extractor class that will be used, followed by a brace-enclosed list of parameters for the builder. This function will construct the appropriate clsfy_builder_1d derivative and return that.

Exceptions: