marf.Classification.Distance
Class Distance

java.lang.Object
  marf.Classification.Classification
      marf.Classification.Distance.Distance

All Implemented Interfaces:

StorageManager

Direct Known Subclasses:

ChebyshevDistance, EuclideanDistance, MahalanobisDistance, MinkowskiDistance

public abstract class Distance

extends Classification

Class Distance

Abstract Distance Classifier

$Header: /cvsroot/marf/marf/src/marf/Classification/Distance/Distance.java,v 1.16 2003/08/17 01:45:25 mokhov Exp $

Field Summary

Fields inherited from class marf.Classification.Classification

oFeatureExtraction, oResult, oTrainingSet

Fields inherited from interface marf.Storage.StorageManager

DUMP_BINARY, DUMP_CSV_TEXT, DUMP_GZIP_BINARY, DUMP_XML

Constructor Summary

Distance(FeatureExtraction poFeatureExtraction)
Distance Constructor

Method Summary

boolean	classify() Classify the feature vector based on whatever distance() derivatives implement.
abstract double	distance(double[] paVector1, double[] paVector2) Generic distance routine.

Methods inherited from class marf.Classification.Classification

dump, getResult, restore, train

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Distance

public Distance(FeatureExtraction poFeatureExtraction)

Distance Constructor

Parameters:

poFeatureExtraction - FeatureExtraction module reference

Method Detail

classify

public final boolean classify()
                       throws ClassificationException

Classify the feature vector based on whatever distance() derivatives implement.

Specified by:

classify in class Classification

Returns:

true if classification successful whatever that means

Throws:

ClassificationException

distance

public abstract double distance(double[] paVector1,
                                double[] paVector2)

Generic distance routine. To be overriden.

Returns:

distance between two vectors