#include "cluster.h"
#include "genericheap.h"
#include "kdpair.h"
#include "matrix.h"
#include "tprintf.h"
#include "helpers.h"
#include <cfloat>
#include <cmath>
#include <vector>

Classes
struct	tesseract::TEMPCLUSTER

struct	tesseract::STATISTICS

struct	tesseract::BUCKETS

struct	tesseract::CHISTRUCT

struct	tesseract::ClusteringContext

Namespaces
namespace	tesseract

Macros
#define	_USE_MATH_DEFINES

#define	HOTELLING 1

#define	FTABLE_X 10

#define	FTABLE_Y 100

#define	MINVARIANCE 0.0004

#define	MINSAMPLESPERBUCKET 5

#define	MINSAMPLES (MINBUCKETS * MINSAMPLESPERBUCKET)

#define	MINSAMPLESNEEDED 1

#define	BUCKETTABLESIZE 1024

#define	NORMALEXTENT 3.0

#define	Odd(N) ((N) % 2)

#define	Mirror(N, R) ((R) - (N)-1)

#define	Abs(N) (((N) < 0) ? (-(N)) : (N))

#define	SqrtOf2Pi 2.506628275

#define	LOOKUPTABLESIZE 8

#define	MAXDEGREESOFFREEDOM MAXBUCKETS

#define	MAXNEIGHBORS 2

#define	MAXDISTANCE FLT_MAX

#define	CHIACCURACY 0.01

#define	MINALPHA (1e-200)

#define	INITIALDELTA 0.1

#define	DELTARATIO 0.1

#define	ILLEGAL_CHAR 2

Typedefs
using	tesseract::ClusterPair = tesseract::KDPairInc< float, TEMPCLUSTER * >

using	tesseract::ClusterHeap = tesseract::GenericHeap< ClusterPair >

using	tesseract::DENSITYFUNC = double(*)(int32_t)

using	tesseract::SOLVEFUNC = double()(CHISTRUCT , double)

Functions
CLUSTERER *	tesseract::MakeClusterer (int16_t SampleSize, const PARAM_DESC ParamDesc[])

SAMPLE *	tesseract::MakeSample (CLUSTERER Clusterer, const float Feature, uint32_t CharID)

LIST	tesseract::ClusterSamples (CLUSTERER Clusterer, CLUSTERCONFIG Config)

void	tesseract::FreeClusterer (CLUSTERER *Clusterer)

void	tesseract::FreeProtoList (LIST *ProtoList)

void	tesseract::FreePrototype (void *arg)

CLUSTER *	tesseract::NextSample (LIST *SearchState)

float	tesseract::Mean (PROTOTYPE *Proto, uint16_t Dimension)

float	tesseract::StandardDeviation (PROTOTYPE *Proto, uint16_t Dimension)

int32_t	tesseract::MergeClusters (int16_t N, PARAM_DESC ParamDesc[], int32_t n1, int32_t n2, float m[], float m1[], float m2[])

Variables
const double	tesseract::FTable [FTABLE_Y][FTABLE_X]

Macro Definition Documentation

◆ _USE_MATH_DEFINES

#define _USE_MATH_DEFINES

Definition at line 18 of file cluster.cpp.

◆ Abs

#define Abs ( N ) (((N) < 0) ? (-(N)) : (N))

Definition at line 1316 of file cluster.cpp.

◆ BUCKETTABLESIZE

#define BUCKETTABLESIZE 1024

define the size of the table which maps normalized samples to histogram buckets. Also define the number of standard deviations in a normal distribution which are considered to be significant. The mapping table will be defined in such a way that it covers the specified number of standard deviations on either side of the mean. BUCKETTABLESIZE should always be even.

Definition at line 1254 of file cluster.cpp.

◆ CHIACCURACY

#define CHIACCURACY 0.01

◆ DELTARATIO

#define DELTARATIO 0.1

◆ FTABLE_X

#define FTABLE_X 10

Definition at line 36 of file cluster.cpp.

◆ FTABLE_Y

#define FTABLE_Y 100

Definition at line 37 of file cluster.cpp.

◆ HOTELLING

#define HOTELLING 1

Definition at line 35 of file cluster.cpp.

◆ ILLEGAL_CHAR

#define ILLEGAL_CHAR 2

◆ INITIALDELTA

#define INITIALDELTA 0.1

◆ LOOKUPTABLESIZE

#define LOOKUPTABLESIZE 8

define lookup tables used to compute the number of histogram buckets that should be used for a given number of samples.

Definition at line 1335 of file cluster.cpp.

◆ MAXDEGREESOFFREEDOM

#define MAXDEGREESOFFREEDOM MAXBUCKETS

Definition at line 1336 of file cluster.cpp.

◆ MAXDISTANCE

#define MAXDISTANCE FLT_MAX

◆ MAXNEIGHBORS

#define MAXNEIGHBORS 2

◆ MINALPHA

#define MINALPHA (1e-200)

◆ MINSAMPLES

#define MINSAMPLES (MINBUCKETS * MINSAMPLESPERBUCKET)

Definition at line 1245 of file cluster.cpp.

◆ MINSAMPLESNEEDED

#define MINSAMPLESNEEDED 1

Definition at line 1246 of file cluster.cpp.

◆ MINSAMPLESPERBUCKET

#define MINSAMPLESPERBUCKET 5

define the absolute minimum number of samples which must be present in order to accurately test hypotheses about underlying probability distributions. Define separately the minimum samples that are needed before a statistical analysis is attempted; this number should be equal to MINSAMPLES but can be set to a lower number for early testing when very few samples are available.

Definition at line 1244 of file cluster.cpp.

◆ MINVARIANCE

#define MINVARIANCE 0.0004

define the variance which will be used as a minimum variance for any dimension of any feature. Since most features are calculated from numbers with a precision no better than 1 in 128, the variance should never be less than the square of this number for parameters whose range is 1.

Definition at line 1236 of file cluster.cpp.

◆ Mirror

#define Mirror	(	N,
		R
	)	((R) - (N)-1)

Definition at line 1315 of file cluster.cpp.

◆ NORMALEXTENT

#define NORMALEXTENT 3.0

Definition at line 1255 of file cluster.cpp.

◆ Odd

#define Odd ( N ) ((N) % 2)

Definition at line 1314 of file cluster.cpp.

◆ SqrtOf2Pi

#define SqrtOf2Pi 2.506628275

the following variables describe a discrete normal distribution which is used by NormalDensity() and NormalBucket(). The constant NORMALEXTENT determines how many standard deviations of the distribution are mapped onto the fixed discrete range of x. x=0 is mapped to -NORMALEXTENT standard deviations and x=BUCKETTABLESIZE is mapped to +NORMALEXTENT standard deviations.

Definition at line 1326 of file cluster.cpp.

Classes

Namespaces

Macros

Typedefs

Functions

Variables