mftraining.cpp

一ＯＣＲ的相关资料。．希望对研究ＯＣＲ的朋友有所帮助．

/******************************************************************************
**	Filename:	mfTraining.c
**	Purpose:	Separates training pages into files for each character.
**				Strips from files only the features and there parameters of
				the feature type mf.
**	Author:		Dan Johnson
**	Revisment:	Christy Russon
**	Environment: HPUX 6.5
**	Library:     HPUX 6.5
**	History:     Fri Aug 18 08:53:50 1989, DSJ, Created.
**		     5/25/90, DSJ, Adapted to multiple feature types.
**				Tuesday, May 17, 1998 Changes made to make feature specific and
**				simplify structures. First step in simplifying training process.
**
 **	(c) Copyright Hewlett-Packard Company, 1988.
 ** Licensed under the Apache License, Version 2.0 (the "License");
 ** you may not use this file except in compliance with the License.
 ** You may obtain a copy of the License at
 ** http://www.apache.org/licenses/LICENSE-2.0
 ** Unless required by applicable law or agreed to in writing, software
 ** distributed under the License is distributed on an "AS IS" BASIS,
 ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 ** See the License for the specific language governing permissions and
 ** limitations under the License.
******************************************************************************/
/**----------------------------------------------------------------------------
					Include Files and Type Defines
----------------------------------------------------------------------------**/
#include "oldlist.h"
#include "efio.h"
#include "emalloc.h"
#include "featdefs.h"
#include "getopt.h"
#include "ocrfeatures.h"
#include "general.h"
#include "clusttool.h"
#include "cluster.h"
#include "protos.h"
#include "minmax.h"
#include "debug.h"
#include "const.h"
#include "mergenf.h"
#include "name2char.h"
#include "intproto.h"
#include "variables.h"
#include "freelist.h"

#include <string.h>
#include <stdio.h>
#include <math.h>

#define MAXNAMESIZE	80
#define MAX_NUM_SAMPLES	10000
#define PROGRAM_FEATURE_TYPE "mf"
#define MINSD (1.0f / 128.0f)

int	row_number;						/* cjn: fixes link problem */

typedef struct
{
  char		*Label;
  LIST		List;
}
LABELEDLISTNODE, *LABELEDLIST;

typedef struct
{
	char* Label;
	int	NumMerged[MAX_NUM_PROTOS];
	CLASS_TYPE Class;
}MERGE_CLASS_NODE;
typedef MERGE_CLASS_NODE* MERGE_CLASS;

#define round(x,frag)(floor(x/frag+.5)*frag)


/**----------------------------------------------------------------------------
					Public Function Prototypes
----------------------------------------------------------------------------**/
int main (
     int	argc,
     char	**argv);

/**----------------------------------------------------------------------------
					Private Function Prototypes
----------------------------------------------------------------------------**/
void ParseArguments(
int	argc,
char	**argv);

char *GetNextFilename ();

LIST ReadTrainingSamples (
     FILE	*File);

LABELEDLIST FindList (
     LIST	List,
     char	*Label);

MERGE_CLASS FindClass (
     LIST	List,
     char	*Label);

LABELEDLIST NewLabeledList (
     char	*Label);

MERGE_CLASS NewLabeledClass (
     char	*Label);

void WriteTrainingSamples (
     char	*Directory,
     LIST	CharList);

void WriteClusteredTrainingSamples (
     char	*Directory,
     LIST	ProtoList,
	 CLUSTERER *Clusterer,
	 LABELEDLIST CharSample);
/**/
void WriteMergedTrainingSamples(
    char	*Directory,
	LIST ClassList);

void WriteMicrofeat(
    char	*Directory,
	LIST	ClassList);

void WriteProtos(
	FILE* File,
	MERGE_CLASS MergeClass);

void WriteConfigs(
	FILE* File,
	CLASS_TYPE Class);

void FreeTrainingSamples (
     LIST	CharList);

void FreeLabeledClassList (
     LIST	ClassList);

void FreeLabeledList (
     LABELEDLIST	LabeledList);

CLUSTERER *SetUpForClustering(
     LABELEDLIST	CharSample);
/*
PARAMDESC *ConvertToPARAMDESC(
	PARAM_DESC* Param_Desc,
	int N);
*/
LIST RemoveInsignificantProtos(
	LIST ProtoList,
	BOOL8 KeepSigProtos,
	BOOL8 KeepInsigProtos,
	int N);

void CleanUpUnusedData(
	LIST ProtoList);

void Normalize (
   float  *Values);

void SetUpForFloat2Int(
	LIST LabeledClassList);

void WritePFFMTable(INT_TEMPLATES Templates, const char* filename) {
  FILE* fp = Efopen(filename, "wb");
  /* then write out each class */
  for (int i = 0; i < NumClassesIn (Templates); i++) {
    int MaxLength = 0;
    INT_CLASS Class = ClassForIndex (Templates, i);
    for (int ConfigId = 0; ConfigId < NumIntConfigsIn (Class); ConfigId++) {
      if (LengthForConfigId (Class, ConfigId) > MaxLength)
        MaxLength = LengthForConfigId (Class, ConfigId);
    }
    fprintf(fp, "%c %d\n", ClassIdForIndex(Templates, i), MaxLength);
  }
  fclose(fp);
}


//--------------Global Data Definitions and Declarations--------------
static char FontName[MAXNAMESIZE];
// globals used for parsing command line arguments
static char	*Directory = NULL;
static int	MaxNumSamples = MAX_NUM_SAMPLES;
static int	Argc;
static char	**Argv;

// globals used to control what information is saved in the output file
static BOOL8		ShowAllSamples = FALSE;
static BOOL8		ShowSignificantProtos = TRUE;
static BOOL8		ShowInsignificantProtos = FALSE;

// global variable to hold configuration parameters to control clustering
// -M 0.40   -B 0.05   -I 1.0   -C 1e-6.
static CLUSTERCONFIG Config =
{ elliptical, 0.40, 0.05, 1.0, 1e-6 };

static FLOAT32 RoundingAccuracy = 0.0;

/*----------------------------------------------------------------------------
						Public Code
-----------------------------------------------------------------------------*/
/*---------------------------------------------------------------------------*/
int main (
     int	argc,
     char	**argv)

/*
**	Parameters:
**		argc	number of command line arguments
**		argv	array of command line arguments
**	Globals: none
**	Operation:
**		This program reads in a text file consisting of feature
**		samples from a training page in the following format:
**
**			FontName CharName NumberOfFeatureTypes(N)
**			   FeatureTypeName1 NumberOfFeatures(M)
**			      Feature1
**			      ...
**			      FeatureM
**			   FeatureTypeName2 NumberOfFeatures(M)
**			      Feature1
**			      ...
**			      FeatureM
**			   ...
**			   FeatureTypeNameN NumberOfFeatures(M)
**			      Feature1
**			      ...
**			      FeatureM
**			FontName CharName ...
**
**		The result of this program is a binary inttemp file used by
**		the OCR engine.
**	Return: none
**	Exceptions: none
**	History:	Fri Aug 18 08:56:17 1989, DSJ, Created.
**				Mon May 18 1998, Christy Russson, Revistion started.
*/

{
	char	*PageName;
	FILE	*TrainingPage;
	FILE	*OutFile;
	LIST	CharList;
	CLUSTERER	*Clusterer = NULL;
	LIST		ProtoList = NIL;
	LABELEDLIST CharSample;
	PROTOTYPE	*Prototype;
	LIST   	ClassList = NIL;
	int		Cid, Pid;
	PROTO		Proto;
	PROTO_STRUCT	DummyProto;
	BIT_VECTOR	Config2;
	MERGE_CLASS	MergeClass;
	INT_TEMPLATES	IntTemplates;
	LIST pCharList, pProtoList;
	char Filename[MAXNAMESIZE];

	ParseArguments (argc, argv);
	InitFastTrainerVars ();
	InitSubfeatureVars ();
	while ((PageName = GetNextFilename()) != NULL)
	{
		printf ("\nReading %s ...", PageName);
		TrainingPage = Efopen (PageName, "r");
		CharList = ReadTrainingSamples (TrainingPage);
		fclose (TrainingPage);
		//WriteTrainingSamples (Directory, CharList);
		pCharList = CharList;
		iterate(pCharList)
		{
			//Cluster
			CharSample = (LABELEDLIST) first (pCharList);
			printf ("\nClustering %s ...", CharSample->Label);
			Clusterer = SetUpForClustering(CharSample);
			ProtoList = ClusterSamples(Clusterer, &Config);
			//WriteClusteredTrainingSamples (Directory, ProtoList, Clusterer, CharSample);
			CleanUpUnusedData(ProtoList);

			//Merge
			ProtoList = RemoveInsignificantProtos(ProtoList, ShowSignificantProtos,
				ShowInsignificantProtos, Clusterer->SampleSize);
			FreeClusterer(Clusterer);
			MergeClass = FindClass (ClassList, CharSample->Label);
			if (MergeClass == NULL)
			{
				MergeClass = NewLabeledClass (CharSample->Label);
				ClassList = push (ClassList, MergeClass);
			}
			Cid = AddConfigToClass(MergeClass->Class);
			pProtoList = ProtoList;
			iterate (pProtoList)
			{
				Prototype = (PROTOTYPE *) first (pProtoList);

				// see if proto can be approximated by existing proto
				Pid = FindClosestExistingProto (MergeClass->Class, MergeClass->NumMerged, Prototype);
				if (Pid == NO_PROTO)
				{
					Pid = AddProtoToClass (MergeClass->Class);
					Proto = ProtoIn (MergeClass->Class, Pid);
					MakeNewFromOld (Proto, Prototype);
					MergeClass->NumMerged[Pid] = 1;
				}
				else
				{
					MakeNewFromOld (&DummyProto, Prototype);
					ComputeMergedProto (ProtoIn (MergeClass->Class, Pid), &DummyProto,
						(FLOAT32) MergeClass->NumMerged[Pid], 1.0,
						ProtoIn (MergeClass->Class, Pid));
					MergeClass->NumMerged[Pid] ++;
				}
				Config2 = ConfigIn (MergeClass->Class, Cid);
				AddProtoToConfig (Pid, Config2);
			}
			FreeProtoList (&ProtoList);
		}
		FreeTrainingSamples (CharList);
		printf ("\n");
	}
	//WriteMergedTrainingSamples(Directory,ClassList);
	WriteMicrofeat(Directory, ClassList);
	InitIntProtoVars ();
	InitPrototypes ();
	SetUpForFloat2Int(ClassList);
	IntTemplates = CreateIntTemplates(TrainingData);
	strcpy (Filename, "");
	if (Directory != NULL)
	{
		strcat (Filename, Directory);
		strcat (Filename, "/");
	}
	strcat (Filename, "inttemp");
#ifdef __UNIX__
	OutFile = Efopen (Filename, "w");
#else
	OutFile = Efopen (Filename, "wb");
#endif
	WriteIntTemplates(OutFile, IntTemplates);
	fclose (OutFile);
  // Now create pffmtable.
  WritePFFMTable(IntTemplates, "pffmtable");
	printf ("\nDone!\n"); /**/
	FreeLabeledClassList (ClassList);
  return 0;
}	/* main */


/**----------------------------------------------------------------------------
							Private Code
----------------------------------------------------------------------------**/
/*---------------------------------------------------------------------------*/
void ParseArguments(
int	argc,
char	**argv)

/*
**	Parameters:
**		argc	number of command line arguments to parse
**		argv	command line arguments
**	Globals:
**		ShowAllSamples		flag controlling samples display
**		ShowSignificantProtos	flag controlling proto display
**		ShowInsignificantProtos	flag controlling proto display
**		Config			current clustering parameters
**		optarg, optind		defined by getopt sys call
**		Argc, Argv		global copies of argc and argv
**	Operation:
**		This routine parses the command line arguments that were
**		passed to the program.  The legal arguments are:
**			-d		"turn off display of samples"
**			-p		"turn off significant protos"
**			-n		"turn off insignificant proto"
**			-S [ spherical | elliptical | mixed | automatic ]
**			-M MinSamples	"min samples per prototype (%)"
**			-B MaxIllegal	"max illegal chars per cluster (%)"
**			-I Independence	"0 to 1"
**			-C Confidence	"1e-200 to 1.0"
**			-D Directory
**			-N MaxNumSamples
**			-R RoundingAccuracy
**	Return: none
**	Exceptions: Illegal options terminate the program.
**	History: 7/24/89, DSJ, Created.
*/

{
	int		Option;
	int		ParametersRead;
	BOOL8		Error;
	extern char	*optarg;

	Error = FALSE;
	Argc = argc;
	Argv = argv;
	while (( Option = getopt( argc, argv, "R:N:D:C:I:M:B:S:d:n:p" )) != EOF )
	{
		switch ( Option )
		{