// Extracts features from the given blob and saves them in the tr_file_data_
// member variable.
// fontname: Name of font that this blob was printed in.
// cn_denorm: Character normalization transformation to apply to the blob.
// fx_info: Character normalization parameters computed with cn_denorm.
// blob_text: Ground truth text for the blob.
void Classify::LearnBlob(const STRING& fontname, TBLOB* blob,
const DENORM& cn_denorm,
const INT_FX_RESULT_STRUCT& fx_info,
const char* blob_text) {
CHAR_DESC CharDesc = NewCharDescription(feature_defs_);
CharDesc->FeatureSets[0] = ExtractMicros(blob, cn_denorm);
CharDesc->FeatureSets[1] = ExtractCharNormFeatures(fx_info);
CharDesc->FeatureSets[2] = ExtractIntCNFeatures(*blob, fx_info);
CharDesc->FeatureSets[3] = ExtractIntGeoFeatures(*blob, fx_info);
if (ValidCharDescription(feature_defs_, CharDesc)) {
// Label the features with a class name and font name.
tr_file_data_ += "\n";
tr_file_data_ += fontname;
tr_file_data_ += " ";
tr_file_data_ += blob_text;
tr_file_data_ += "\n";
// write micro-features to file and clean up
WriteCharDescription(feature_defs_, CharDesc, &tr_file_data_);
} else {
tprintf("Blob learned was invalid!\n");
}
FreeCharDescription(CharDesc);
} // LearnBlob
/*---------------------------------------------------------------------------*/
CHAR_DESC ReadCharDescription(FILE *File) {
/*
** Parameters:
** File open text file to read character description from
** Globals: none
** Operation: Read a character description from File, and return
** a data structure containing this information. The data
** is formatted as follows:
** NumberOfSets
** ShortNameForSet1 Set1
** ShortNameForSet2 Set2
** ...
** Return: Character description read from File.
** Exceptions: ILLEGAL_NUM_SETS
** History: Wed May 23 17:32:48 1990, DSJ, Created.
*/
int NumSetsToRead;
char ShortName[FEAT_NAME_SIZE];
CHAR_DESC CharDesc;
int Type;
if (fscanf (File, "%d", &NumSetsToRead) != 1 ||
NumSetsToRead < 0 || NumSetsToRead > NumFeaturesDefined ())
DoError (ILLEGAL_NUM_SETS, "Illegal number of feature sets");
CharDesc = NewCharDescription ();
for (; NumSetsToRead > 0; NumSetsToRead--) {
fscanf (File, "%s", ShortName);
Type = ShortNameToFeatureType (ShortName);
FeaturesOfType (CharDesc, Type) =
ReadFeatureSet (File, DefinitionOf (Type));
}
return (CharDesc);
} // ReadCharDescription
/**
* Read a character description from File, and return
* a data structure containing this information. The data
* is formatted as follows:
* @verbatim
NumberOfSets
ShortNameForSet1 Set1
ShortNameForSet2 Set2
...
@endverbatim
*
* Globals:
* - none
*
* @param FeatureDefs definitions of feature types/extractors
* @param File open text file to read character description from
* @return Character description read from File.
* @note Exceptions:
* - ILLEGAL_NUM_SETS
* @note History: Wed May 23 17:32:48 1990, DSJ, Created.
*/
CHAR_DESC ReadCharDescription(const FEATURE_DEFS_STRUCT &FeatureDefs,
FILE *File) {
int NumSetsToRead;
char ShortName[FEAT_NAME_SIZE];
CHAR_DESC CharDesc;
int Type;
if (fscanf (File, "%d", &NumSetsToRead) != 1 ||
NumSetsToRead < 0 || NumSetsToRead > FeatureDefs.NumFeatureTypes)
DoError (ILLEGAL_NUM_SETS, "Illegal number of feature sets");
CharDesc = NewCharDescription(FeatureDefs);
for (; NumSetsToRead > 0; NumSetsToRead--) {
fscanf (File, "%s", ShortName);
Type = ShortNameToFeatureType(FeatureDefs, ShortName);
CharDesc->FeatureSets[Type] =
ReadFeatureSet (File, FeatureDefs.FeatureDesc[Type]);
}
return (CharDesc);
} // ReadCharDescription