mftraining.cpp

来自「一个google的OCR源码」· C++ 代码 · 共 1,342 行 · 第 1/3 页

/******************************************************************************
**	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 "tessopt.h"
#include "ocrfeatures.h"
#include "mf.h"
#include "general.h"
#include "clusttool.h"
#include "cluster.h"
#include "protos.h"
#include "minmax.h"
#include "debug.h"
#include "tprintf.h"
#include "const.h"
#include "mergenf.h"
#include "name2char.h"
#include "intproto.h"
#include "variables.h"
#include "freelist.h"
#include "efio.h"
#include "danerror.h"
#include "globals.h"

#include <string.h>
#include <stdio.h>
#define _USE_MATH_DEFINES
#include <math.h>
#ifdef WIN32
#ifndef M_PI
#define M_PI 3.14159265358979323846
#endif
#endif

#define MAXNAMESIZE	80
#define MAX_NUM_SAMPLES	10000
#define PROGRAM_FEATURE_TYPE "mf"
#define MINSD (1.0f / 128.0f)
#define MINSD_ANGLE (1.0f / 64.0f)

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

typedef struct
{
  char		*Label;
  int       SampleCount;
  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);
*/
void MergeInsignificantProtos(LIST ProtoList, const char* label,
                              CLUSTERER	*Clusterer, CLUSTERCONFIG *Config);

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);

//--------------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, 0.625, 0.05, 1.0, 1e-6, 0 };

static FLOAT32 RoundingAccuracy = 0.0f;

// The unicharset used during mftraining
static UNICHARSET unicharset_mftraining;

const char* test_ch = "";

/*----------------------------------------------------------------------------
						Public Code
-----------------------------------------------------------------------------*/
void DisplayProtoList(const char* ch, LIST protolist) {
  void* window = c_create_window("Char samples", 50, 200,
                                 520, 520, -130.0, 130.0, -130.0, 130.0);
  LIST proto = protolist;
  iterate(proto) {
    PROTOTYPE* prototype = reinterpret_cast<PROTOTYPE *>(first_node(proto));
    if (prototype->Significant)
      c_line_color_index(window, Green);
    else if (prototype->NumSamples == 0)
      c_line_color_index(window, Blue);
    else if (prototype->Merged)
      c_line_color_index(window, Magenta);
    else
      c_line_color_index(window, Red);
    float x = CenterX(prototype->Mean);
    float y = CenterY(prototype->Mean);
    double angle = OrientationOf(prototype->Mean) * 2 * M_PI;
    float dx = static_cast<float>(LengthOf(prototype->Mean) * cos(angle) / 2);
    float dy = static_cast<float>(LengthOf(prototype->Mean) * sin(angle) / 2);
    c_move(window, (x - dx) * 256, (y - dy) * 256);
    c_draw(window, (x + dx) * 256, (y + dy) * 256);
    if (prototype->Significant)
      tprintf("Green proto at (%g,%g)+(%g,%g) %d samples\n",
              x, y, dx, dy, prototype->NumSamples);
    else if (prototype->NumSamples > 0 && !prototype->Merged)
      tprintf("Red proto at (%g,%g)+(%g,%g) %d samples\n",
              x, y, dx, dy, prototype->NumSamples);
  }
  c_make_current(window);
}

/*---------------------------------------------------------------------------*/
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];

  // Clean the unichar set
  unicharset_mftraining.clear();
  // Space character needed to represent NIL classification
  unicharset_mftraining.unichar_insert(" ");

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

      //Merge
      MergeInsignificantProtos(ProtoList, CharSample->Label,
                               Clusterer, &Config);
      if (strcmp(test_ch, CharSample->Label) == 0)
        DisplayProtoList(test_ch, ProtoList);
      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_node (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);
  }
  //WriteMergedTrainingSamples(Directory,ClassList);
  WriteMicrofeat(Directory, ClassList);
  InitIntProtoVars ();
  InitPrototypes ();
  SetUpForFloat2Int(ClassList);
  IntTemplates = CreateIntTemplates(TrainingData, unicharset_mftraining);
  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, unicharset_mftraining);
  fclose (OutFile);
  strcpy (Filename, "");
  if (Directory != NULL) {
    strcat (Filename, Directory);
    strcat (Filename, "/");
  }
  strcat (Filename, "pffmtable");
  // Now create pffmtable.
  WritePFFMTable(IntTemplates, Filename);
  printf ("Done!\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
**		tessoptarg, tessoptind		defined by tessopt 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;

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