Main Page   Class Hierarchy   Alphabetical List   Compound List   Compound Members  

prapi::extras::JHDistance Class Reference

#include <ExtraProximities.h>

Inheritance diagram for prapi::extras::JHDistance:

prapi::ProximityMeasure< double > Object List of all members.

Detailed Description

A proximity measure represented in "Jain A and Healey G (1998) A Multiscale Representation Including Opponent Color Features for Texture Recognition.

IEEE Trans. on Image Proc. 7(1):124-128. In short, this measure is a squared Euclidean distance scaled with feature variances.


Public Methods

 JHDistance (const util::List< Sample< double > > &allSamples)
 Create a new "Jain and Healey" type distance measure.

double getProximity (const util::List< double > &sample, const util::List< double > &model, double stopAfter=MAXDOUBLE) const throw (ProximityException&)


Constructor & Destructor Documentation

prapi::extras::JHDistance::JHDistance const util::List< Sample< double > > &    allSamples
 

Create a new "Jain and Healey" type distance measure.

This measure needs a set of samples at initialization because it needs to calculate the variance of each feature.

Parameters:
allSamples  the samples between which distances are calculated


The documentation for this class was generated from the following files:
Documentation generated on 11.09.2003 with Doxygen.
The documentation is copyrighted material.
Copyright © Topi Mäenpää 2003. All rights reserved.