Main Page | Class Hierarchy | Class List | Directories | File List | Class Members | File Members

Seg_Model Class Reference

A class representing a segmentation model. More...

#include <Seg_Model.hpp>

Inheritance diagram for Seg_Model:

HMRF IID_Mixture List of all members.

Public Member Functions

virtual ~Seg_Model ()
 destructor
uint Get_D ()
 Get dimension.
uint Get_K ()
 Get the number of classes.
virtual double LogLikelihood (Spatial_Data *spatd)
 Likelihood.
virtual double Completed_LogLikelihood (Spatial_Data *spatd, vector< double > tik)
 Completed likelihood.
virtual double BIC (Spatial_Data *spatd)
 BIC -- Bayesian Information Criterion.
virtual double ICL (Spatial_Data *spatd)
 ICL -- Integrated Completed Likelihood.
double LogDensity (vector< double > const &X, uint k)
 Compute the log-density for observation X in class k.
double Density (vector< double > const &X, uint k)
 Compute the density for observation X in class k.
void Estimate_Distributions (Spatial_Data *spatd, vector< double > const &tik)
 Estimate the distributions parameters.
virtual uint Degrees_Of_Freedom ()
 Number of free parameters.
virtual void Info ()
 Display model information.
virtual void Estimate (Spatial_Data *spatd, vector< double > const &tik)
 Estimate model parameters.

Protected Attributes

vector< Distribution * > Distrib
 Distributions.

Detailed Description

Author:
Lemine Abdallahi
Date:
Aug. 2005
Abstract class.


Constructor & Destructor Documentation

Seg_Model::~Seg_Model  )  [virtual]
 

Destructor.

Abstract. Model-dependent.


Member Function Documentation

double Seg_Model::BIC Spatial_Data spatd  )  [virtual]
 

Compute the BIC -- Bayesian Information Criterion.

Parameters:
[in] spatd : Spatial data (observations).
Returns:
the value of the BIC.
Abstract. Model-dependent.

Reimplemented in HMRF, and IID_Mixture.

double Seg_Model::Completed_LogLikelihood Spatial_Data spatd,
vector< double >  tik
[virtual]
 

Compute the Completed likelihood.

Parameters:
[in] spatd : Spatial data (observations).
[in] tik : fuzzy classifications
Returns:
the value of the completed likelihhood.
Abstract. Model-dependent.

uint Seg_Model::Degrees_Of_Freedom  )  [virtual]
 

Number of free parameters.

Returns:
the degrees of freedom of the MRF model.
Abstract. Model-dependent.

Reimplemented in HMRF, and IID_Mixture.

double Seg_Model::Density vector< double > const &  X,
uint  k
 

Compute density at X in the class k, i.e. , f(X | mu_k, sigma_k)

uint Seg_Model::Get_D  ) 
 

Get the dimension

uint Seg_Model::Get_K  ) 
 

Get the number of classes/colors.

Returns:
The number of classes/colors in the MRF.

double Seg_Model::ICL Spatial_Data spatd  )  [virtual]
 

Compute the ICL -- Integrated Completed Likelihood

Parameters:
[in] spatd : Spatial data (observations).
Returns:
the value of the ICL.
Abstract. Model-dependent.

Reimplemented in HMRF, and IID_Mixture.

void Seg_Model::Info  )  [virtual]
 

Print some info on the model.

Abstract. Model-dependent.

Reimplemented in HMRF, and IID_Mixture.

double Seg_Model::LogDensity vector< double > const &  X,
uint  k
 

Compute log density at X in the class k, i.e. , log f(X | mu_k, sigma_k)

double Seg_Model::LogLikelihood Spatial_Data spatd  )  [virtual]
 

Comptue the Log-Likelihood

Parameters:
[in] spatd : Spatial data (observations).
Returns:
the value of the log-likelihood.
Abstract. Model-dependent.

Reimplemented in HMRF, and IID_Mixture.


The documentation for this class was generated from the following files:
Generated on Thu Jan 12 11:55:04 2006 for NEM by  doxygen 1.4.4