mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2025-06-08 02:12:40 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

doxygen training/commontraining.cpp

Browse Source
This commit is contained in:
Jim O'Regan 2015-07-20 17:34:29 +01:00
parent cc5f466ac6
commit cce044fa66
1 changed files with 112 additions and 135 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

247
training/commontraining.cpp
View File

@ -73,18 +73,17 @@ DOUBLE_PARAM_FLAG(clusterconfig_independence, Config.Independence,
DOUBLE_PARAM_FLAG(clusterconfig_confidence, Config.Confidence, DOUBLE_PARAM_FLAG(clusterconfig_confidence, Config.Confidence,
"Desired confidence in prototypes created"); "Desired confidence in prototypes created");
/* /**
** Parameters: * This routine parses the command line arguments that were
** argc number of command line arguments to parse * passed to the program and ses them to set relevant
** argv command line arguments * training-related global parameters
** Globals: *
** Config current clustering parameters * Globals:
** Operation: * - Config current clustering parameters
** This routine parses the command line arguments that were * @param argc number of command line arguments to parse
** passed to the program and ses them to set relevant * @parm argv command line arguments
** training-related global parameters * @return none
** Return: none * @note Exceptions: Illegal options terminate the program.
** Exceptions: Illegal options terminate the program.
*/ */
void ParseArguments(int* argc, char ***argv) { void ParseArguments(int* argc, char ***argv) {
STRING usage; STRING usage;
@ -158,19 +157,21 @@ void WriteShapeTable(const STRING& file_prefix, const ShapeTable& shape_table) {
} }
} }
// Creates a MasterTraininer and loads the training data into it: /**
// Initializes feature_defs and IntegerFX. * Creates a MasterTraininer and loads the training data into it:
// Loads the shape_table if shape_table != NULL. * Initializes feature_defs and IntegerFX.
// Loads initial unicharset from -U command-line option. * Loads the shape_table if shape_table != NULL.
// If FLAGS_T is set, loads the majority of data from there, else: * Loads initial unicharset from -U command-line option.
// Loads font info from -F option. * If FLAGS_T is set, loads the majority of data from there, else:
// Loads xheights from -X option. * - Loads font info from -F option.
// Loads samples from .tr files in remaining command-line args. * - Loads xheights from -X option.
// Deletes outliers and computes canonical samples. * - Loads samples from .tr files in remaining command-line args.
// If FLAGS_output_trainer is set, saves the trainer for future use. * - Deletes outliers and computes canonical samples.
// Computes canonical and cloud features. * - If FLAGS_output_trainer is set, saves the trainer for future use.
// If shape_table is not NULL, but failed to load, make a fake flat one, * Computes canonical and cloud features.
// as shape clustering was not run. * If shape_table is not NULL, but failed to load, make a fake flat one,
* as shape clustering was not run.
*/
MasterTrainer* LoadTrainingData(int argc, const char* const * argv, MasterTrainer* LoadTrainingData(int argc, const char* const * argv,
bool replication, bool replication,
ShapeTable** shape_table, ShapeTable** shape_table,
@ -294,20 +295,19 @@ MasterTrainer* LoadTrainingData(int argc, const char* const * argv,
} // namespace tesseract. } // namespace tesseract.
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
const char *GetNextFilename(int argc, const char* const * argv) { /**
/* * This routine returns the next command line argument. If
** Parameters: none * there are no remaining command line arguments, it returns
** Globals: * NULL. This routine should only be called after all option
** tessoptind defined by tessopt sys call * arguments have been parsed and removed with ParseArguments.
** Operation: *
** This routine returns the next command line argument. If * Globals:
** there are no remaining command line arguments, it returns * - tessoptind defined by tessopt sys call
** NULL. This routine should only be called after all option * @return Next command line argument or NULL.
** arguments have been parsed and removed with ParseArguments. * @note Exceptions: none
** Return: Next command line argument or NULL. * @note History: Fri Aug 18 09:34:12 1989, DSJ, Created.
** Exceptions: none
** History: Fri Aug 18 09:34:12 1989, DSJ, Created.
*/ */
const char *GetNextFilename(int argc, const char* const * argv) {
if (tessoptind < argc) if (tessoptind < argc)
return argv[tessoptind++]; return argv[tessoptind++];
else else
@ -317,24 +317,20 @@ const char *GetNextFilename(int argc, const char* const * argv) {
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
/**
* 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.
* @param List list to search
* @param Label label to search for
* @return Labeled list with the specified Label or NULL.
* @note Globals: none
* @note Exceptions: none
* @note History: Fri Aug 18 15:57:41 1989, DSJ, Created.
*/
LABELEDLIST FindList ( LABELEDLIST FindList (
LIST List, LIST List,
char *Label) 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; LABELEDLIST LabeledList;
@ -349,21 +345,17 @@ LABELEDLIST FindList (
} /* FindList */ } /* FindList */
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
/**
* This routine allocates a new, empty labeled list and gives
* it the specified label.
* @param Label label for new list
* @return New, empty labeled list.
* @note Globals: none
* @note Exceptions: none
* @note History: Fri Aug 18 16:08:46 1989, DSJ, Created.
*/
LABELEDLIST NewLabeledList ( LABELEDLIST NewLabeledList (
const char *Label) const 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;
@ -380,25 +372,24 @@ LABELEDLIST NewLabeledList (
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
// TODO(rays) This is now used only by cntraining. Convert cntraining to use // TODO(rays) This is now used only by cntraining. Convert cntraining to use
// the new method or get rid of it entirely. // the new method or get rid of it entirely.
/**
* This routine reads training samples from a file and
* places them into a data structure which organizes the
* samples by FontName and CharName. It then returns this
* data structure.
* @param file open text file to read samples from
* @return none
* @note Globals: none
* @note Exceptions: none
* @note 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.
*/
void ReadTrainingSamples(const FEATURE_DEFS_STRUCT& feature_defs, void ReadTrainingSamples(const FEATURE_DEFS_STRUCT& feature_defs,
const char *feature_name, int max_samples, const char *feature_name, int max_samples,
UNICHARSET* unicharset, UNICHARSET* unicharset,
FILE* file, LIST* training_samples) { FILE* file, LIST* training_samples) {
/*
** Parameters:
** file open text file to read samples from
** Globals: none
** Operation:
** This routine reads training samples from a file and
** places them into a data structure which organizes the
** samples by FontName and CharName. It then returns this
** data structure.
** Return: none
** Exceptions: none
** 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 buffer[2048]; char buffer[2048];
char unichar[UNICHAR_LEN + 1]; char unichar[UNICHAR_LEN + 1];
LABELEDLIST char_sample; LABELEDLIST char_sample;
@ -450,18 +441,16 @@ void ReadTrainingSamples(const FEATURE_DEFS_STRUCT& feature_defs,
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
void FreeTrainingSamples(LIST CharList) { /**
/* * This routine deallocates all of the space allocated to
** Parameters: * the specified list of training samples.
** FontList list of all fonts in document * @param FontList list of all fonts in document
** Globals: none * @return none
** Operation: * @note Globals: none
** This routine deallocates all of the space allocated to * @note Exceptions: none
** the specified list of training samples. * @note History: Fri Aug 18 17:44:27 1989, DSJ, Created.
** Return: none
** Exceptions: none
** History: Fri Aug 18 17:44:27 1989, DSJ, Created.
*/ */
void FreeTrainingSamples(LIST CharList) {
LABELEDLIST char_sample; LABELEDLIST char_sample;
FEATURE_SET FeatureSet; FEATURE_SET FeatureSet;
LIST FeatureList; LIST FeatureList;
@ -480,45 +469,37 @@ void FreeTrainingSamples(LIST CharList) {
} /* FreeTrainingSamples */ } /* FreeTrainingSamples */
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
void FreeLabeledList(LABELEDLIST LabeledList) { /**
/* * This routine deallocates all of the memory consumed by
** Parameters: * a labeled list. It does not free any memory which may be
** LabeledList labeled list to be freed * consumed by the items in the list.
** Globals: none * @param LabeledList labeled list to be freed
** Operation: * @note Globals: none
** This routine deallocates all of the memory consumed by * @return none
** a labeled list. It does not free any memory which may be * @note Exceptions: none
** consumed by the items in the list. * @note History: Fri Aug 18 17:52:45 1989, DSJ, Created.
** Return: none
** Exceptions: none
** History: Fri Aug 18 17:52:45 1989, DSJ, Created.
*/ */
void FreeLabeledList(LABELEDLIST LabeledList) {
destroy(LabeledList->List); destroy(LabeledList->List);
free(LabeledList->Label); free(LabeledList->Label);
free(LabeledList); free(LabeledList);
} /* FreeLabeledList */ } /* FreeLabeledList */
/*---------------------------------------------------------------------------*/ /*---------------------------------------------------------------------------*/
/**
* 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.
* @param char_sample: LABELEDLIST that holds all the feature information for a
* given character.
* @return Pointer to new clusterer data structure.
* @note Globals: None
* @note Exceptions: None
* @note History: 8/16/89, DSJ, Created.
*/
CLUSTERER *SetUpForClustering(const FEATURE_DEFS_STRUCT &FeatureDefs, CLUSTERER *SetUpForClustering(const FEATURE_DEFS_STRUCT &FeatureDefs,
LABELEDLIST char_sample, LABELEDLIST char_sample,
const char* program_feature_type) { const char* program_feature_type) {
/*
** Parameters:
** char_sample: 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; uinT16 N;
int i, j; int i, j;
FLOAT32 *Sample = NULL; FLOAT32 *Sample = NULL;
@ -741,21 +722,17 @@ MERGE_CLASS NewLabeledClass (
} /* NewLabeledClass */ } /* NewLabeledClass */
/*-----------------------------------------------------------------------------*/ /*-----------------------------------------------------------------------------*/
/**
* This routine deallocates all of the space allocated to
* the specified list of training samples.
* @param FontList list of all fonts in document
* @return none
* @note Globals: none
* @note Exceptions: none
* @note History: Fri Aug 18 17:44:27 1989, DSJ, Created.
*/
void FreeLabeledClassList ( void FreeLabeledClassList (
LIST ClassList) LIST ClassList)
/*
** 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.
*/
{ {
MERGE_CLASS MergeClass; MERGE_CLASS MergeClass;
@ -770,7 +747,7 @@ void FreeLabeledClassList (
} /* FreeLabeledClassList */ } /* FreeLabeledClassList */
/** SetUpForFloat2Int **************************************************/ /* SetUpForFloat2Int */
CLASS_STRUCT* SetUpForFloat2Int(const UNICHARSET& unicharset, CLASS_STRUCT* SetUpForFloat2Int(const UNICHARSET& unicharset,
LIST LabeledClassList) { LIST LabeledClassList) {
MERGE_CLASS MergeClass; MERGE_CLASS MergeClass;