cntraining.cpp

来自「一个google的OCR源码」· C++ 代码 · 共 856 行 · 第 1/2 页

**	History: Fri Aug 18 13:11:39 1989, DSJ, Created.
**			 Tue May 17 1998 simplifications to structure, illiminated
**				font, and feature specification levels of structure.
*/

{
	char		unichar[UNICHAR_LEN + 1];
	LABELEDLIST	CharSample;
	FEATURE_SET	FeatureSamples;
	CHAR_DESC	CharDesc;
	int		Type, i;

	while (fscanf (File, "%s %s", FontName, unichar) == 2) {
          CharSample = FindList (*TrainingSamples, unichar);
          if (CharSample == NULL) {
            CharSample = NewLabeledList (unichar);
            *TrainingSamples = push (*TrainingSamples, CharSample);
          }
          CharDesc = ReadCharDescription (File);
          Type = ShortNameToFeatureType(PROGRAM_FEATURE_TYPE);
          FeatureSamples = FeaturesOfType(CharDesc, Type);
          for (int feature = 0; feature < FeatureSamples->NumFeatures; ++feature) {
            FEATURE f = FeatureSamples->Features[feature];
            for (int dim =0; dim < f->Type->NumParams; ++dim)
              f->Params[dim] += UniformRandomNumber(-MINSD, MINSD);
          }
          CharSample->List = push (CharSample->List, FeatureSamples);
          CharSample->SampleCount++;
          for (i = 0; i < NumFeatureSetsIn (CharDesc); i++)
            if (Type != i)
              FreeFeatureSet (FeaturesOfType (CharDesc, i));
          free (CharDesc);
        }
}	// ReadTrainingSamples

/*---------------------------------------------------------------------------*/
LABELEDLIST FindList (
     LIST	List,
     char	*Label)

/*
**	Parameters:
**		List		list to search
**		Label		label to search for
**	Globals: none
**	Operation:
**		This routine searches thru a list of labeled lists to find
**		a list with the specified label.  If a matching labeled list
**		cannot be found, NULL is returned.
**	Return: Labeled list with the specified Label or NULL.
**	Exceptions: none
**	History: Fri Aug 18 15:57:41 1989, DSJ, Created.
*/

{
	LABELEDLIST	LabeledList;

	iterate (List)
    {
		LabeledList = (LABELEDLIST) first_node (List);
		if (strcmp (LabeledList->Label, Label) == 0)
			return (LabeledList);
    }
	return (NULL);

}	/* FindList */

/*---------------------------------------------------------------------------*/
LABELEDLIST NewLabeledList (
     char	*Label)

/*
**	Parameters:
**		Label	label for new list
**	Globals: none
**	Operation:
**		This routine allocates a new, empty labeled list and gives
**		it the specified label.
**	Return: New, empty labeled list.
**	Exceptions: none
**	History: Fri Aug 18 16:08:46 1989, DSJ, Created.
*/

{
	LABELEDLIST	LabeledList;

	LabeledList = (LABELEDLIST) (char*)Emalloc (sizeof (LABELEDLISTNODE));
	LabeledList->Label = (char*)Emalloc (strlen (Label)+1);
	strcpy (LabeledList->Label, Label);
	LabeledList->List = NIL;
    LabeledList->SampleCount = 0;
	return (LabeledList);

}	/* NewLabeledList */

/*---------------------------------------------------------------------------*/
void WriteTrainingSamples (
     char	*Directory,
     LIST	CharList)

/*
**	Parameters:
**		Directory	directory to place sample files into
**		FontList	list of fonts used in the training samples
**	Globals:
**		MaxNumSamples	max number of samples per class to write
**	Operation:
**		This routine writes the specified samples into files which
**		are organized according to the font name and character name
**		of the samples.
**	Return: none
**	Exceptions: none
**	History: Fri Aug 18 16:17:06 1989, DSJ, Created.
*/

{
	LABELEDLIST	CharSample;
	FEATURE_SET	FeatureSet;
	LIST		FeatureList;
	FILE		*File;
	char		Filename[MAXNAMESIZE];
	int		NumSamples;

	iterate (CharList)		// iterate thru all of the fonts
	{
		CharSample = (LABELEDLIST) first_node (CharList);

		// construct the full pathname for the current samples file
		strcpy (Filename, "");
		if (Directory != NULL)
		{
			strcat (Filename, Directory);
			strcat (Filename, "/");
		}
		strcat (Filename, "Merged");
		strcat (Filename, "/");
		strcat (Filename, CharSample->Label);
		strcat (Filename, ".");
		strcat (Filename, PROGRAM_FEATURE_TYPE);
		printf ("\nWriting %s ...", Filename);

		/* if file does not exist, create a new one with an appropriate
		header; otherwise append samples to the existing file */
		File = fopen (Filename, "r");
		if (File == NULL)
		{
			File = Efopen (Filename, "w");
			WriteOldParamDesc
				(File, DefinitionOf (ShortNameToFeatureType (PROGRAM_FEATURE_TYPE)));
		}
		else
		{
			fclose (File);
			File = Efopen (Filename, "a");
		}

		// append samples onto the file
		FeatureList = CharSample->List;
		NumSamples = 0;
		iterate (FeatureList)
		{
			//if (NumSamples >= MaxNumSamples) break;

			FeatureSet = (FEATURE_SET) first_node (FeatureList);
			WriteFeatureSet (File, FeatureSet);
			NumSamples++;
		}
		fclose (File);
	}
}	/* WriteTrainingSamples */


/*----------------------------------------------------------------------------*/
void WriteNormProtos (
     char	*Directory,
     LIST	LabeledProtoList,
	 CLUSTERER *Clusterer)

/*
**	Parameters:
**		Directory	directory to place sample files into
**	Globals:
**		MaxNumSamples	max number of samples per class to write
**	Operation:
**		This routine writes the specified samples into files which
**		are organized according to the font name and character name
**		of the samples.
**	Return: none
**	Exceptions: none
**	History: Fri Aug 18 16:17:06 1989, DSJ, Created.
*/

{
	FILE		*File;
	char		Filename[MAXNAMESIZE];
	LABELEDLIST LabeledProto;
	int N;

	strcpy (Filename, "");
	if (Directory != NULL)
	{
		strcat (Filename, Directory);
		strcat (Filename, "/");
	}
	strcat (Filename, "normproto");
	printf ("\nWriting %s ...", Filename);
	File = Efopen (Filename, "w");
	fprintf(File,"%0d\n",Clusterer->SampleSize);
	WriteParamDesc(File,Clusterer->SampleSize,Clusterer->ParamDesc);
	iterate(LabeledProtoList)
	{
		LabeledProto = (LABELEDLIST) first_node (LabeledProtoList);
		N = NumberOfProtos(LabeledProto->List,
		ShowSignificantProtos, ShowInsignificantProtos);
                if (N < 1) {
                  printf ("\nError! Not enough protos for %s: %d protos"
                          " (%d significant protos"
                          ", %d insignificant protos)\n",
                          LabeledProto->Label, N,
                          NumberOfProtos(LabeledProto->List, 1, 0),
                          NumberOfProtos(LabeledProto->List, 0, 1));
                  exit(1);
                }
		fprintf(File, "\n%s %d\n", LabeledProto->Label, N);
		WriteProtos(File, Clusterer->SampleSize, LabeledProto->List,
			ShowSignificantProtos, ShowInsignificantProtos);
	}
	fclose (File);

}	// WriteNormProtos

/*---------------------------------------------------------------------------*/
void FreeTrainingSamples (
     LIST	CharList)

/*
**	Parameters:
**		FontList	list of all fonts in document
**	Globals: none
**	Operation:
**		This routine deallocates all of the space allocated to
**		the specified list of training samples.
**	Return: none
**	Exceptions: none
**	History: Fri Aug 18 17:44:27 1989, DSJ, Created.
*/

{
	LABELEDLIST	CharSample;
	FEATURE_SET	FeatureSet;
	LIST		FeatureList;


	printf ("\nFreeTrainingSamples...");
	iterate (CharList) 		/* iterate thru all of the fonts */
	{
		CharSample = (LABELEDLIST) first_node (CharList);
		FeatureList = CharSample->List;
		iterate (FeatureList)	/* iterate thru all of the classes */
		{
			FeatureSet = (FEATURE_SET) first_node (FeatureList);
			FreeFeatureSet (FeatureSet);
		}
		FreeLabeledList (CharSample);
	}
	destroy (CharList);

}	/* FreeTrainingSamples */

/*-------------------------------------------------------------------------*/
void FreeNormProtoList (
     LIST	CharList)

{
	LABELEDLIST	CharSample;

	iterate (CharList) 		/* iterate thru all of the fonts */
	{
		CharSample = (LABELEDLIST) first_node (CharList);
		FreeLabeledList (CharSample);
	}
	destroy (CharList);

}	// FreeNormProtoList

/*---------------------------------------------------------------------------*/
void FreeLabeledList (
     LABELEDLIST	LabeledList)

/*
**	Parameters:
**		LabeledList	labeled list to be freed
**	Globals: none
**	Operation:
**		This routine deallocates all of the memory consumed by
**		a labeled list.  It does not free any memory which may be
**		consumed by the items in the list.
**	Return: none
**	Exceptions: none
**	History: Fri Aug 18 17:52:45 1989, DSJ, Created.
*/

{
	destroy (LabeledList->List);
	free (LabeledList->Label);
	free (LabeledList);

}	/* FreeLabeledList */

/*---------------------------------------------------------------------------*/
CLUSTERER *SetUpForClustering(
     LABELEDLIST	CharSample)

/*
**	Parameters:
**		CharSample: LABELEDLIST that holds all the feature information for a
**		given character.
**	Globals:
**		None
**	Operation:
**		This routine reads samples from a LABELEDLIST and enters
**		those samples into a clusterer data structure.  This
**		data structure is then returned to the caller.
**	Return:
**		Pointer to new clusterer data structure.
**	Exceptions:
**		None
**	History:
**		8/16/89, DSJ, Created.
*/

{
	uinT16	N;
	int		i, j;
	FLOAT32	*Sample = NULL;
	CLUSTERER	*Clusterer;
	inT32		CharID;
	LIST FeatureList = NULL;
	FEATURE_SET FeatureSet = NULL;
	FEATURE_DESC FeatureDesc = NULL;
//	PARAM_DESC* ParamDesc;

	FeatureDesc = DefinitionOf(ShortNameToFeatureType(PROGRAM_FEATURE_TYPE));
	N = FeatureDesc->NumParams;
	//ParamDesc = ConvertToPARAMDESC(FeatureDesc->ParamDesc, N);
	Clusterer = MakeClusterer(N,FeatureDesc->ParamDesc);
//	free(ParamDesc);

	FeatureList = CharSample->List;
	CharID = 0;
	iterate(FeatureList)
	{
		FeatureSet = (FEATURE_SET) first_node (FeatureList);
		for (i=0; i < FeatureSet->MaxNumFeatures; i++)
		{
			if (Sample == NULL)
				Sample = (FLOAT32 *)Emalloc(N * sizeof(FLOAT32));
			for (j=0; j < N; j++)
				if (RoundingAccuracy != 0.0)
					Sample[j] = round(FeatureSet->Features[i]->Params[j], RoundingAccuracy);
				else
					Sample[j] = FeatureSet->Features[i]->Params[j];
				MakeSample (Clusterer, Sample, CharID);
		}
		CharID++;
	}
	if ( Sample != NULL ) free( Sample );
	return( Clusterer );

}	/* SetUpForClustering */

/*---------------------------------------------------------------------------*/
void AddToNormProtosList(
	LIST* NormProtoList,
	LIST ProtoList,
	char* CharName)
{
	PROTOTYPE* Proto;
	LABELEDLIST LabeledProtoList;

	LabeledProtoList = NewLabeledList(CharName);
	iterate(ProtoList)
	{
		Proto = (PROTOTYPE *) first_node (ProtoList);
		LabeledProtoList->List = push(LabeledProtoList->List, Proto);
	}
	*NormProtoList = push(*NormProtoList, LabeledProtoList);
}

/*-------------------------------------------------------------------------*/
void WriteProtos(
     FILE	*File,
     uinT16	N,
     LIST	ProtoList,
     BOOL8	WriteSigProtos,
     BOOL8	WriteInsigProtos)
{
	PROTOTYPE	*Proto;

	// write prototypes
	iterate(ProtoList)
	{
		Proto = (PROTOTYPE *) first_node ( ProtoList );
		if (( Proto->Significant && WriteSigProtos )	||
			( ! Proto->Significant && WriteInsigProtos ) )
			WritePrototype( File, N, Proto );
	}
}	// WriteProtos

/*---------------------------------------------------------------------------*/
int NumberOfProtos(
	LIST ProtoList,
    BOOL8	CountSigProtos,
    BOOL8	CountInsigProtos)
{
	int N = 0;
	PROTOTYPE	*Proto;

	iterate(ProtoList)
	{
		Proto = (PROTOTYPE *) first_node ( ProtoList );
		if (( Proto->Significant && CountSigProtos )	||
			( ! Proto->Significant && CountInsigProtos ) )
			N++;
	}
	return(N);
}