Tesseract  3.02
tesseract-ocr/classify/blobclass.cpp File Reference
#include "blobclass.h"
#include "extract.h"
#include "efio.h"
#include "featdefs.h"
#include "callcpp.h"
#include "chartoname.h"
#include <math.h>
#include <stdio.h>
#include <signal.h>

Go to the source code of this file.


#define MAXFILENAME   80
#define MAXMATCHES   10
#define TRAIN_SUFFIX   ".tr"


void LearnBlob (const FEATURE_DEFS_STRUCT &FeatureDefs, const STRING &filename, TBLOB *Blob, const DENORM &denorm, const char *BlobText)
void LearnBlob (const FEATURE_DEFS_STRUCT &FeatureDefs, FILE *FeatureFile, TBLOB *Blob, const DENORM &denorm, const char *BlobText, const char *FontName)


char * classify_font_name = kUnknownFontName
char imagefile []

Define Documentation

#define MAXFILENAME   80

---------------------------------------------------------------------------- Include Files and Type Defines ----------------------------------------------------------------------------

Definition at line 33 of file blobclass.cpp.

#define MAXMATCHES   10

Definition at line 34 of file blobclass.cpp.

#define TRAIN_SUFFIX   ".tr"

Function Documentation

void LearnBlob ( const FEATURE_DEFS_STRUCT FeatureDefs,
const STRING filename,
const DENORM denorm,
const char *  BlobText 

---------------------------------------------------------------------------- Public Code ----------------------------------------------------------------------------

Definition at line 52 of file blobclass.cpp.

 **      Parameters:
 **              Blob            blob whose micro-features are to be learned
 **              Row             row of text that blob came from
 **              BlobText        text that corresponds to blob
 **              TextLength      number of characters in blob
 **      Globals:
 **              imagefile       base filename of the page being learned
 **              classify_font_name
 **                              name of font currently being trained on
 **      Operation:
 **              Extract micro-features from the specified blob and append
 **              them to the appropriate file.
 **      Return: none
 **      Exceptions: none
 **      History: 7/28/89, DSJ, Created.
#define TRAIN_SUFFIX    ".tr"
  static FILE *FeatureFile = NULL;
  STRING Filename(filename);

  // If no fontname was set, try to extract it from the filename
  STRING CurrFontName = classify_font_name;
  if (CurrFontName == kUnknownFontName) {
    // filename is expected to be of the form [lang].[fontname].exp[num]
    // The [lang], [fontname] and [num] fields should not have '.' characters.
    const char *basename = strrchr(filename.string(), '/');
    const char *firstdot = strchr(basename ? basename : filename.string(), '.');
    const char *lastdot  = strrchr(filename.string(), '.');
    if (firstdot != lastdot && firstdot != NULL && lastdot != NULL) {
      CurrFontName = firstdot;
      CurrFontName[lastdot - firstdot] = '\0';

  // if a feature file is not yet open, open it
  // the name of the file is the name of the image plus TRAIN_SUFFIX
  if (FeatureFile == NULL) {
    Filename += TRAIN_SUFFIX;
    FeatureFile = Efopen(Filename.string(), "wb");
    cprintf("TRAINING ... Font name = %s\n", CurrFontName.string());

  LearnBlob(FeatureDefs, FeatureFile, Blob, denorm, BlobText,
}                                // LearnBlob
void LearnBlob ( const FEATURE_DEFS_STRUCT FeatureDefs,
FILE *  FeatureFile,
const DENORM denorm,
const char *  BlobText,
const char *  FontName 

Definition at line 102 of file blobclass.cpp.

  CHAR_DESC CharDesc;

  ASSERT_HOST(FeatureFile != NULL);

  CharDesc = ExtractBlobFeatures(FeatureDefs, denorm, Blob);
  if (CharDesc == NULL) {
    cprintf("LearnBLob: CharDesc was NULL. Aborting.\n");

  if (ValidCharDescription(FeatureDefs, CharDesc)) {
    // label the features with a class name and font name
    fprintf(FeatureFile, "\n%s %s\n", FontName, BlobText);

    // write micro-features to file and clean up
    WriteCharDescription(FeatureDefs, FeatureFile, CharDesc);
  } else {
    tprintf("Blob learned was invalid!\n");

}                                // LearnBlob

Variable Documentation

char* classify_font_name = kUnknownFontName

"Default font name to be used in training"

Definition at line 39 of file blobclass.cpp.

char imagefile[]

---------------------------------------------------------------------------- Global Data Definitions and Declarations ----------------------------------------------------------------------------