cntraining.cpp File Reference

#include "oldlist.h"
#include "efio.h"
#include "emalloc.h"
#include "featdefs.h"
#include "tessopt.h"
#include "ocrfeatures.h"
#include "clusttool.h"
#include "cluster.h"
#include <string.h>
#include <stdio.h>
#include <math.h>
#include "unichar.h"
#include "commontraining.h"

Go to the source code of this file.

Macros
#define	PROGRAM_FEATURE_TYPE   "cn"

Functions
	DECLARE_STRING_PARAM_FLAG (D)
int	main (int argc, char **argv)
void	WriteNormProtos (const char *Directory, LIST LabeledProtoList, const FEATURE_DESC_STRUCT *feature_desc)
void	WriteProtos (FILE *File, uinT16 N, LIST ProtoList, BOOL8 WriteSigProtos, BOOL8 WriteInsigProtos)
int	main (int argc, char *argv[])

Variables
CLUSTERCONFIG	CNConfig

Macro Definition Documentation

PROGRAM_FEATURE_TYPE

#define PROGRAM_FEATURE_TYPE   "cn"

Definition at line 40 of file cntraining.cpp.

Function Documentation

DECLARE_STRING_PARAM_FLAG()

DECLARE_STRING_PARAM_FLAG

(

D

)

main() [1/2]

int main	(	int	argc,
		char **	argv
	)

This program reads in a text file consisting of feature samples from a training page in the following format:

   FontName UTF8-char-str xmin ymin xmax ymax page-number
    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.

Parameters

argc	number of command line arguments
argv	array of command line arguments

Returns

none

Note

Exceptions: none

History: Fri Aug 18 08:56:17 1989, DSJ, Created.

History: Mon May 18 1998, Christy Russson, Revistion started.

Definition at line 388 of file tesseractmain.cpp.

                                {
  const char* lang = "eng";
  const char* image = NULL;
  const char* outputbase = NULL;
  const char* datapath = NULL;
  bool list_langs = false;
  bool print_parameters = false;
  int arg_i = 1;
  tesseract::PageSegMode pagesegmode = tesseract::PSM_AUTO;
  tesseract::OcrEngineMode enginemode = tesseract::OEM_DEFAULT;
  /* main() calls functions like ParseArgs which call exit().
   * This results in memory leaks if vars_vec and vars_values are
   * declared as auto variables (destructor is not called then). */
  static GenericVector<STRING> vars_vec;
  static GenericVector<STRING> vars_values;

#ifdef NDEBUG
  // Disable debugging and informational messages from Leptonica.
  setMsgSeverity(L_SEVERITY_ERROR);
#endif

#if defined(HAVE_TIFFIO_H) && defined(_WIN32)
  /* Show libtiff warnings on console (not in GUI). */
  TIFFSetWarningHandler(Win32WarningHandler);
#endif /* HAVE_TIFFIO_H &&  _WIN32 */

  ParseArgs(argc, argv, &lang, &image, &outputbase, &datapath, &list_langs,
            &print_parameters, &vars_vec, &vars_values, &arg_i, &pagesegmode,
            &enginemode);

  bool banner = false;
  if (outputbase != NULL && strcmp(outputbase, "-") &&
      strcmp(outputbase, "stdout")) {
    banner = true;
  }

  PERF_COUNT_START("Tesseract:main")

  // Call GlobalDawgCache here to create the global DawgCache object before
  // the TessBaseAPI object. This fixes the order of destructor calls:
  // first TessBaseAPI must be destructed, DawgCache must be the last object.
  tesseract::Dict::GlobalDawgCache();

  // Avoid memory leak caused by auto variable when exit() is called.
  static tesseract::TessBaseAPI api;

  api.SetOutputName(outputbase);

  int init_failed = api.Init(datapath, lang, enginemode, &(argv[arg_i]),
                             argc - arg_i, &vars_vec, &vars_values, false);
  if (init_failed) {
    fprintf(stderr, "Could not initialize tesseract.\n");
    return EXIT_FAILURE;
  }

  SetVariablesFromCLArgs(&api, argc, argv);

  if (list_langs) {
    PrintLangsList(&api);
    return EXIT_SUCCESS;
  }

  if (print_parameters) {
     FILE* fout = stdout;
     fprintf(stdout, "Tesseract parameters:\n");
     api.PrintVariables(fout);
     api.End();
     return EXIT_SUCCESS;
  }

  FixPageSegMode(&api, pagesegmode);

  if (pagesegmode == tesseract::PSM_AUTO_ONLY) {
    int ret_val = EXIT_SUCCESS;

    Pix* pixs = pixRead(image);
    if (!pixs) {
      fprintf(stderr, "Cannot open input file: %s\n", image);
      return 2;
    }

    api.SetImage(pixs);

    tesseract::Orientation orientation;
    tesseract::WritingDirection direction;
    tesseract::TextlineOrder order;
    float deskew_angle;

    tesseract::PageIterator* it = api.AnalyseLayout();
    if (it) {
      it->Orientation(&orientation, &direction, &order, &deskew_angle);
      tprintf(
          "Orientation: %d\nWritingDirection: %d\nTextlineOrder: %d\n"
          "Deskew angle: %.4f\n",
          orientation, direction, order, deskew_angle);
    } else {
      ret_val = EXIT_FAILURE;
    }

    delete it;

    pixDestroy(&pixs);
    return ret_val;
  }

  // set in_training_mode to true when using one of these configs:
  // ambigs.train, box.train, box.train.stderr, linebox, rebox
  bool b = false;
  bool in_training_mode =
      (api.GetBoolVariable("tessedit_ambigs_training", &b) && b) ||
      (api.GetBoolVariable("tessedit_resegment_from_boxes", &b) && b) ||
      (api.GetBoolVariable("tessedit_make_boxes_from_boxes", &b) && b);

  // Avoid memory leak caused by auto variable when exit() is called.
  static tesseract::PointerVector<tesseract::TessResultRenderer> renderers;

  if (in_training_mode) {
    renderers.push_back(NULL);
  } else {
    PreloadRenderers(&api, &renderers, pagesegmode, outputbase);
  }

  if (!renderers.empty()) {
    if (banner) PrintBanner();
    bool succeed = api.ProcessPages(image, NULL, 0, renderers[0]);
    if (!succeed) {
      fprintf(stderr, "Error during processing.\n");
      return EXIT_FAILURE;
    }
  }

  PERF_COUNT_END

  return EXIT_SUCCESS;
}

main() [2/2]

int main	(	int	argc,
		char *	argv[]
	)

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 ...

It then appends these samples into a separate file for each character. The name of the file is

DirectoryName/FontName/CharName.FeatureTypeName

The DirectoryName can be specified via a command line argument. If not specified, it defaults to the current directory. The format of the resulting files is:

   NumberOfFeatures(M)
      Feature1
      ...
      FeatureM
   NumberOfFeatures(M)
   ...

The output files each have a header which describes the type of feature which the file contains. This header is in the format required by the clusterer. A command line argument can also be used to specify that only the first N samples of each class should be used.

Parameters

argc	number of command line arguments
argv	array of command line arguments

Returns

none

Note

Globals: none

Exceptions: none

History: Fri Aug 18 08:56:17 1989, DSJ, Created.

Definition at line 133 of file cntraining.cpp.

                                 {
  // Set the global Config parameters before parsing the command line.
  Config = CNConfig;

  const char  *PageName;
  FILE  *TrainingPage;
  LIST  CharList = NIL_LIST;
  CLUSTERER  *Clusterer = NULL;
  LIST    ProtoList = NIL_LIST;
  LIST    NormProtoList = NIL_LIST;
  LIST pCharList;
  LABELEDLIST CharSample;
  FEATURE_DEFS_STRUCT FeatureDefs;
  InitFeatureDefs(&FeatureDefs);

  ParseArguments(&argc, &argv);
  int num_fonts = 0;
  while ((PageName = GetNextFilename(argc, argv)) != NULL) {
    printf("Reading %s ...\n", PageName);
    TrainingPage = Efopen(PageName, "rb");
    ReadTrainingSamples(FeatureDefs, PROGRAM_FEATURE_TYPE,
                        100, NULL, TrainingPage, &CharList);
    fclose(TrainingPage);
    ++num_fonts;
  }
  printf("Clustering ...\n");
  // To allow an individual font to form a separate cluster,
  // reduce the min samples:
  // Config.MinSamples = 0.5 / num_fonts;
  pCharList = CharList;
  // The norm protos will count the source protos, so we keep them here in
  // freeable_protos, so they can be freed later.
  GenericVector<LIST> freeable_protos;
  iterate(pCharList) {
    //Cluster
    CharSample = (LABELEDLIST)first_node(pCharList);
    Clusterer =
      SetUpForClustering(FeatureDefs, CharSample, PROGRAM_FEATURE_TYPE);
    if (Clusterer == NULL) {  // To avoid a SIGSEGV
      fprintf(stderr, "Error: NULL clusterer!\n");
      return 1;
    }
    float SavedMinSamples = Config.MinSamples;
    // To disable the tendency to produce a single cluster for all fonts,
    // make MagicSamples an impossible to achieve number:
    // Config.MagicSamples = CharSample->SampleCount * 10;
    Config.MagicSamples = CharSample->SampleCount;
    while (Config.MinSamples > 0.001) {
      ProtoList = ClusterSamples(Clusterer, &Config);
      if (NumberOfProtos(ProtoList, 1, 0) > 0) {
        break;
      } else {
        Config.MinSamples *= 0.95;
        printf("0 significant protos for %s."
               " Retrying clustering with MinSamples = %f%%\n",
               CharSample->Label, Config.MinSamples);
      }
    }
    Config.MinSamples = SavedMinSamples;
    AddToNormProtosList(&NormProtoList, ProtoList, CharSample->Label);
    freeable_protos.push_back(ProtoList);
    FreeClusterer(Clusterer);
  }
  FreeTrainingSamples(CharList);
  int desc_index = ShortNameToFeatureType(FeatureDefs, PROGRAM_FEATURE_TYPE);
  WriteNormProtos(FLAGS_D.c_str(), NormProtoList,
                  FeatureDefs.FeatureDesc[desc_index]);
  FreeNormProtoList(NormProtoList);
  for (int i = 0; i < freeable_protos.size(); ++i) {
    FreeProtoList(&freeable_protos[i]);
  }
  printf ("\n");
  return 0;
}  // main

WriteNormProtos()

void WriteNormProtos	(	const char *	Directory,
		LIST	LabeledProtoList,
		const FEATURE_DESC_STRUCT *	feature_desc
	)

This routine writes the specified samples into files which are organized according to the font name and character name of the samples.

Parameters

Directory	directory to place sample files into
LabeledProtoList	List of labeled protos
feature_desc	Description of the features

Returns

none

Note

Exceptions: none

History: Fri Aug 18 16:17:06 1989, DSJ, Created.

Definition at line 224 of file cntraining.cpp.

                                                              {
  FILE    *File;
  STRING Filename;
  LABELEDLIST LabeledProto;
  int N;

  Filename = "";
  if (Directory != NULL && Directory[0] != '\0')
  {
    Filename += Directory;
    Filename += "/";
  }
  Filename += "normproto";
  printf ("\nWriting %s ...", Filename.string());
  File = Efopen (Filename.string(), "wb");
  fprintf(File, "%0d\n", feature_desc->NumParams);
  WriteParamDesc(File, feature_desc->NumParams, feature_desc->ParamDesc);
  iterate(LabeledProtoList)
  {
    LabeledProto = (LABELEDLIST) first_node (LabeledProtoList);
    N = NumberOfProtos(LabeledProto->List, true, false);
    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, feature_desc->NumParams, LabeledProto->List, true, false);
  }
  fclose (File);

}  // WriteNormProtos

WriteProtos()

void WriteProtos	(	FILE *	File,
		uinT16	N,
		LIST	ProtoList,
		BOOL8	WriteSigProtos,
		BOOL8	WriteInsigProtos
	)

Definition at line 263 of file cntraining.cpp.

{
  PROTOTYPE  *Proto;

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

Variable Documentation

CNConfig

CLUSTERCONFIG CNConfig

Initial value:

=
{
  elliptical, 0.025, 0.05, 0.8, 1e-3, 0
}

Definition at line 76 of file cntraining.cpp.