User Documentation
RAVL, Recognition And Vision Library
DEVELOP HOME PAGE CLASS LIST CONTENTS
Ravl - Pattern Recognition - Classify - ClassifyAverageNearestNeighbourC
 

  PUBLIC
ClassifyAverageNearestNeighbourC::ClassifyAverageNearestNeighbourC(const DataSet2C &,UIntT,const DistanceC &)
ClassifyKNearestNeighbourC::Search(const VectorC &,UIntT)
ClassifyKNearestNeighbourC::K(void) const
ClassifyVectorC::Classify(const VectorC &) const
ClassifyVectorC::Confidence(const VectorC &) const
ClassifyVectorC::Labels(void) const
RCHandleC::operator =(const RCHandleC &)
RCHandleC::DeepCopy(UIntT) const
RCHandleC::operator ==(const RCHandleC &) const
RCHandleC::operator !=(const RCHandleC &) const
RCHandleC::Hash(void) const
RCHandleC::IsValid(void) const
RCHandleC::Invalidate(void)
RCHandleC::IsHandleType(const DT &) const
RCHandleC::CheckHandleType(const DT &) const
RCHandleC::References(void) const
RCHandleC::operator <<(ostream &,const RCHandleC &)
RCHandleC::operator >>(istream &,RCHandleC &)

   ClassifyAverageNearestNeighbourC   
 
ClassifyAverage k nearest neighbour classifier.
 
include "Ravl/PatternRec/ClassifyAverageNearestNeighbour.hh"
User Level:Normal
Library:RavlPatternRec
In Scope:RavlN

Comments:
Amoung the k nearest neighours to the probe choose the label with the smallest average distance.

Parent Classes: Methods:
ClassifyAverageNearestNeighbourC(const DataSet2C<SampleVectorC,SampleLabelC> & data,UIntT defaultK = 5,const DistanceC & xdistMetric = DistanceSqrEuclideanC ())
Constructor.

#include "Ravl/PatternRec/ClassifyKNearestNeighbour.hh"
SArray1dC<Tuple2C<UIntT,RealT>> Search(const VectorC & ex,UIntT k)
Search for the the 'k' nearest neighbours.
Returns the label and the distance for the 'k' nearest neighbours.

UIntT K() const
Number of samples to use when classifying.

#include "Ravl/PatternRec/ClassifyVector.hh"
UIntT Classify(const VectorC & data) const
Classify vector 'data' return the most likely label.

VectorC Confidence(const VectorC & data) const
Estimate the confidence for each label.
The meaning of the confidence assigned to each label depends on the classifier used. The higher the confidence the more likely it is the label is correct.

UIntT Labels() const
Returns the maximum number of output labels.

#include "Ravl/RefCounter.hh"
const RCHandleC<ClassifyVectorBodyC> & operator =(const RCHandleC<ClassifyVectorBodyC> & oth)
Assign handle.

RCHandleC<ClassifyVectorBodyC> DeepCopy(UIntT levels = ((UIntT))) const
Do a deep copy of the object.

bool operator ==(const RCHandleC<ClassifyVectorBodyC> & oth) const
Are handles to the same object ?

bool operator !=(const RCHandleC<ClassifyVectorBodyC> & oth) const
Are handles to different objects ?

UIntT Hash() const
Default hash function.
This hashes on the address of the body.

bool IsValid() const
Test if this is a valid handle.

void Invalidate()
Invalidate this handle.
Unattaches the body from the handle.

bool IsHandleType(const DT &) const
Is handle of given type ?

void CheckHandleType(const DT & dummy) const
Check handle type. Throw an expception if not.

UIntT References() const
Find the number of references to the body of this object.

ostream & operator <<(ostream & strm,const RCHandleC<ClassifyVectorBodyC> & obj)

istream & operator >>(istream & strm,RCHandleC<ClassifyVectorBodyC> & obj)


Maintainer:Charles Galambos, Documentation by CxxDoc: Tue Aug 13 09:59:02 2002