cntraining.cpp

Go to the documentation of this file.

/******************************************************************************
 **  Filename:  cntraining.cpp
 **  Purpose:  Generates a normproto and pffmtable.
 **  Author:    Dan Johnson
 **  Revisment:  Christy Russon
 **
 **  (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 <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"
 
#define PROGRAM_FEATURE_TYPE "cn"
 
using namespace tesseract;
 
/*----------------------------------------------------------------------------
          Private Function Prototypes
----------------------------------------------------------------------------*/
 
static void WriteNormProtos(const char *Directory, LIST LabeledProtoList,
                            const FEATURE_DESC_STRUCT *feature_desc);
 
static void WriteProtos(FILE *File, uint16_t N, LIST ProtoList, bool WriteSigProtos,
                        bool WriteInsigProtos);
 
/*----------------------------------------------------------------------------
          Global Data Definitions and Declarations
----------------------------------------------------------------------------*/
/* global variable to hold configuration parameters to control clustering */
//-M 0.025   -B 0.05   -I 0.8   -C 1e-3
static const CLUSTERCONFIG CNConfig = {elliptical, 0.025, 0.05, 0.8, 1e-3, 0};
 
/*----------------------------------------------------------------------------
              Public Code
----------------------------------------------------------------------------*/
 
int main(int argc, char *argv[]) {
  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
 
/*----------------------------------------------------------------------------
              Private Code
----------------------------------------------------------------------------*/
 
/*----------------------------------------------------------------------------*/
static void WriteNormProtos(const char *Directory, LIST LabeledProtoList,
                            const FEATURE_DESC_STRUCT *feature_desc) {
  FILE *File;
  LABELEDLIST LabeledProto;
  int N;
 
  std::string Filename = "";
  if (Directory != nullptr && Directory[0] != '\0') {
    Filename += Directory;
    Filename += "/";
  }
  Filename += "normproto";
  printf("\nWriting %s ...", Filename.c_str());
  File = fopen(Filename.c_str(), "wb");
  ASSERT_HOST(File);
  fprintf(File, "%0d\n", feature_desc->NumParams);
  WriteParamDesc(File, feature_desc->NumParams, feature_desc->ParamDesc);
  iterate(LabeledProtoList) {
    LabeledProto = reinterpret_cast<LABELEDLIST>(LabeledProtoList->first_node());
    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.c_str(), N, NumberOfProtos(LabeledProto->List, true, false),
          NumberOfProtos(LabeledProto->List, false, true));
      exit(1);
    }
    fprintf(File, "\n%s %d\n", LabeledProto->Label.c_str(), N);
    WriteProtos(File, feature_desc->NumParams, LabeledProto->List, true, false);
  }
  fclose(File);
 
} // WriteNormProtos
 
/*-------------------------------------------------------------------------*/
 
static void WriteProtos(FILE *File, uint16_t N, LIST ProtoList, bool WriteSigProtos,
                        bool WriteInsigProtos) {
  PROTOTYPE *Proto;
 
  // write prototypes
  iterate(ProtoList) {
    Proto = reinterpret_cast<PROTOTYPE *>(ProtoList->first_node());
    if ((Proto->Significant && WriteSigProtos) || (!Proto->Significant && WriteInsigProtos)) {
      WritePrototype(File, N, Proto);
    }
  }
} // WriteProtos