tessbox.cpp

来自「一个google的OCR源码」· C++ 代码 · 共 376 行 · 第 1/2 页

                         ) {
  TWERD *tessword;               //converted word
  inT32 result;                  //answer

  tessword = make_tess_word (word, NULL);
  result = AdaptableWord (tessword, word_choice->string ().string (),
                          word_choice->lengths ().string (),
                          raw_choice->string ().string (),
                          raw_choice->lengths ().string ());
  delete_word(tessword);
  return result != 0;
}


/**********************************************************************
 * tess_cn_matcher
 *
 * Match a blob using the Tess Char Normalized (non-adaptive) matcher
 * only.
 **********************************************************************/

void tess_cn_matcher(                           //call tess
                     PBLOB *pblob,              //previous blob
                     PBLOB *blob,               //blob to match
                     PBLOB *nblob,              //next blob
                     WERD *word,                //word it came from
                     DENORM *denorm,            //de-normaliser
                     BLOB_CHOICE_LIST &ratings  //list of results
                    ) {
  LIST result;                   //tess output
  TBLOB *tessblob;               //converted blob
  TEXTROW tessrow;               //dummy row

  tess_cn_matching = TRUE;       //turn it on
  tess_bn_matching = FALSE;
                                 //convert blob
  tessblob = make_tess_blob (blob, TRUE);
                                 //make dummy row
  make_tess_row(denorm, &tessrow);
                                 //classify
  result = AdaptiveClassifier (tessblob, NULL, &tessrow);
  free_blob(tessblob);
                                 //make our format
  convert_choice_list(result, ratings);
}


/**********************************************************************
 * tess_bn_matcher
 *
 * Match a blob using the Tess Baseline Normalized (adaptive) matcher
 * only.
 **********************************************************************/

void tess_bn_matcher(                           //call tess
                     PBLOB *pblob,              //previous blob
                     PBLOB *blob,               //blob to match
                     PBLOB *nblob,              //next blob
                     WERD *word,                //word it came from
                     DENORM *denorm,            //de-normaliser
                     BLOB_CHOICE_LIST &ratings  //list of results
                    ) {
  LIST result;                   //tess output
  TBLOB *tessblob;               //converted blob
  TEXTROW tessrow;               //dummy row

  tess_bn_matching = TRUE;       //turn it on
  tess_cn_matching = FALSE;
                                 //convert blob
  tessblob = make_tess_blob (blob, TRUE);
                                 //make dummy row
  make_tess_row(denorm, &tessrow);
                                 //classify
  result = AdaptiveClassifier (tessblob, NULL, &tessrow);
  free_blob(tessblob);
                                 //make our format
  convert_choice_list(result, ratings);
}


/**********************************************************************
 * tess_default_matcher
 *
 * Match a blob using the default functionality of the Tess matcher.
 **********************************************************************/

void tess_default_matcher(                           //call tess
                          PBLOB *pblob,              //previous blob
                          PBLOB *blob,               //blob to match
                          PBLOB *nblob,              //next blob
                          WERD *word,                //word it came from
                          DENORM *denorm,            //de-normaliser
                          BLOB_CHOICE_LIST &ratings  //list of results
                         ) {
  LIST result;                   //tess output
  TBLOB *tessblob;               //converted blob
  TEXTROW tessrow;               //dummy row

  tess_bn_matching = FALSE;      //turn it off
  tess_cn_matching = FALSE;
                                 //convert blob
  tessblob = make_tess_blob (blob, TRUE);
                                 //make dummy row
  make_tess_row(denorm, &tessrow);
                                 //classify
  result = AdaptiveClassifier (tessblob, NULL, &tessrow);
  free_blob(tessblob);
                                 //make our format
  convert_choice_list(result, ratings);
}


/**********************************************************************
 * tess_training_tester
 *
 * Matcher tester function which actually trains tess.
 **********************************************************************/

void tess_training_tester(                           //call tess
                          PBLOB *blob,               //blob to match
                          DENORM *denorm,            //de-normaliser
                          BOOL8 correct,             //ly segmented
                          char *text,                //correct text
                          inT32 count,               //chars in text
                          BLOB_CHOICE_LIST *ratings  //list of results
                         ) {
  TBLOB *tessblob;               //converted blob
  TEXTROW tessrow;               //dummy row

  if (correct) {
    NormMethod = character;              //Force char norm spc 30/11/93
    tess_bn_matching = FALSE;    //turn it off
    tess_cn_matching = FALSE;
                                 //convert blob
    tessblob = make_tess_blob (blob, TRUE);
                                 //make dummy row
    make_tess_row(denorm, &tessrow);
                                 //learn it
    LearnBlob(tessblob, &tessrow, text);
    free_blob(tessblob);
  }
}


/**********************************************************************
 * tess_adapter
 *
 * Adapt to the word using the Tesseract mechanism.
 **********************************************************************/

void tess_adapter(                         //adapt to word
                  WERD *word,              //bln word
                  DENORM *denorm,          //de-normalise
                  const WERD_CHOICE& choice,      //string for word
                  const WERD_CHOICE& raw_choice,  //before context
                  const char *rejmap       //reject map
                 ) {
  TWERD *tessword;               //converted word
  static TEXTROW tessrow;        //dummy row

                                 //make dummy row
  make_tess_row(denorm, &tessrow);
                                 //make a word
  tessword = make_tess_word (word, &tessrow);
  AdaptToWord(tessword, &tessrow, choice, raw_choice, rejmap);
  //adapt to it
  delete_word(tessword);  //free it
}


/**********************************************************************
 * tess_add_doc_word
 *
 * Add the given word to the document dictionary
 **********************************************************************/

void tess_add_doc_word(                          //test acceptability
                       WERD_CHOICE *word_choice  //after context
                      ) {
  A_CHOICE choice;               //after context

  choice.rating = word_choice->rating ();
  choice.certainty = word_choice->certainty ();
  choice.string = (char *) word_choice->string ().string ();
  choice.lengths = (char *) word_choice->lengths ().string ();
  add_document_word(&choice);
}