---

prapi::FeatureExtractor< T, U > Class Template Reference

#include <FeatureExtractor.h>

Inheritance diagram for prapi::FeatureExtractor< T, U >:

List of all members.

---

Detailed Description

template<class T, class U>
class prapi::FeatureExtractor< T, U >

FeatureExtractor is an interface for operations that calculate a feature vector out of something.

This is a very general representation as the type of "something" isn't restricted in any way. It may be an image, a speech sample or whatever.

Public Methods
virtual	~FeatureExtractor ()
virtual util::List< T >	getFeatureVector (const U &pattern)=0 throw (FeatureExtractionException&)
	Create a feature vector for a pattern.

---

Member Function Documentation

template<class T, class U> virtual util::List<T> prapi::FeatureExtractor< T, U >::getFeatureVector (  const U &    pattern )  throw (FeatureExtractionException&) [pure virtual]

Create a feature vector for a pattern. In most cases, the length of the returned vector is assumed to be constant for all possible patterns. This assumption is not restrictive, however, and one may use the returned value as needed. Parameters: pattern  a sample Returns: a feature vector Implemented in CoOccurence, GeneralLBP< T >, LBP8, LBP8Color, OpponentColorLBP< T >, ColorCorrelogram, ColorCubeExtractor< T, comps >, ColorPercentile, JHExtractor, prapi::IntegerHistogram, prapi::MultiFeatureHistogram, prapi::MultiDimensionalHistogram, and prapi::GeneralHistogram< T >.

---

The documentation for this class was generated from the following file:

• FeatureExtractor.h

---

Documentation generated on 11.09.2003 with Doxygen.
The documentation is copyrighted material.
Copyright © Topi Mäenpää 2003. All rights reserved.