cntraining.cpp File Reference

#include <tesseract/unichar.h>
#include <cmath>
#include <cstdio>
#include <cstring>
#include "cluster.h"
#include "clusttool.h"
#include "commontraining.h"
#include "featdefs.h"
#include "ocrfeatures.h"
#include "oldlist.h"

Go to the source code of this file.

Macros
#define	PROGRAM_FEATURE_TYPE   "cn"

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

Macro Definition Documentation

PROGRAM_FEATURE_TYPE

#define PROGRAM_FEATURE_TYPE   "cn"

Definition at line 33 of file cntraining.cpp.

Function Documentation

main()

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

0 on success

Definition at line 103 of file cntraining.cpp.

                                 {
  tesseract::CheckSharedLibraryVersion();
 
  // Set the global Config parameters before parsing the command line.
  Config = CNConfig;
 
  LIST CharList = NIL_LIST;
  CLUSTERER *Clusterer = nullptr;
  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;
  for (const char *PageName = *++argv; PageName != nullptr; PageName = *++argv) {
    printf("Reading %s ...\n", PageName);
    FILE *TrainingPage = fopen(PageName, "rb");
    ASSERT_HOST(TrainingPage);
    if (TrainingPage) {
      ReadTrainingSamples(FeatureDefs, PROGRAM_FEATURE_TYPE, 100, nullptr, 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.
  std::vector<LIST> freeable_protos;
  iterate(pCharList) {
    // Cluster
    CharSample = reinterpret_cast<LABELEDLIST>(pCharList->first_node());
    Clusterer = SetUpForClustering(FeatureDefs, CharSample, PROGRAM_FEATURE_TYPE);
    if (Clusterer == nullptr) { // To avoid a SIGSEGV
      fprintf(stderr, "Error: nullptr clusterer!\n");
      return EXIT_FAILURE;
    }
    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, true, false) > 0) {
        break;
      } else {
        Config.MinSamples *= 0.95;
        printf(
            "0 significant protos for %s."
            " Retrying clustering with MinSamples = %f%%\n",
            CharSample->Label.c_str(), 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 (auto &freeable_proto : freeable_protos) {
    FreeProtoList(&freeable_proto);
  }
  printf("\n");
  return EXIT_SUCCESS;
} // main