|
Tesseract
3.02
|
|
Tesseract
3.02
|
#include <classify.h>
Definition at line 58 of file classify.h.
| tesseract::Classify::Classify | ( | ) |
Definition at line 29 of file classify.cpp.
: BOOL_MEMBER(prioritize_division, FALSE, "Prioritize blob division over chopping", this->params()), INT_MEMBER(tessedit_single_match, FALSE, "Top choice only from CP", this->params()), BOOL_MEMBER(classify_enable_learning, true, "Enable adaptive classifier", this->params()), INT_MEMBER(classify_debug_level, 0, "Classify debug level", this->params()), INT_MEMBER(classify_norm_method, character, "Normalization Method ...", this->params()), double_MEMBER(classify_char_norm_range, 0.2, "Character Normalization Range ...", this->params()), double_MEMBER(classify_min_norm_scale_x, 0.0, "Min char x-norm scale ...", this->params()), /* PREV DEFAULT 0.1 */ double_MEMBER(classify_max_norm_scale_x, 0.325, "Max char x-norm scale ...", this->params()), /* PREV DEFAULT 0.3 */ double_MEMBER(classify_min_norm_scale_y, 0.0, "Min char y-norm scale ...", this->params()), /* PREV DEFAULT 0.1 */ double_MEMBER(classify_max_norm_scale_y, 0.325, "Max char y-norm scale ...", this->params()), /* PREV DEFAULT 0.3 */ BOOL_MEMBER(tess_cn_matching, 0, "Character Normalized Matching", this->params()), BOOL_MEMBER(tess_bn_matching, 0, "Baseline Normalized Matching", this->params()), BOOL_MEMBER(classify_enable_adaptive_matcher, 1, "Enable adaptive classifier", this->params()), BOOL_MEMBER(classify_use_pre_adapted_templates, 0, "Use pre-adapted classifier templates", this->params()), BOOL_MEMBER(classify_save_adapted_templates, 0, "Save adapted templates to a file", this->params()), BOOL_MEMBER(classify_enable_adaptive_debugger, 0, "Enable match debugger", this->params()), INT_MEMBER(matcher_debug_level, 0, "Matcher Debug Level", this->params()), INT_MEMBER(matcher_debug_flags, 0, "Matcher Debug Flags", this->params()), INT_MEMBER(classify_learning_debug_level, 0, "Learning Debug Level: ", this->params()), double_MEMBER(matcher_good_threshold, 0.125, "Good Match (0-1)", this->params()), double_MEMBER(matcher_great_threshold, 0.0, "Great Match (0-1)", this->params()), double_MEMBER(matcher_perfect_threshold, 0.02, "Perfect Match (0-1)", this->params()), double_MEMBER(matcher_bad_match_pad, 0.15, "Bad Match Pad (0-1)", this->params()), double_MEMBER(matcher_rating_margin, 0.1, "New template margin (0-1)", this->params()), double_MEMBER(matcher_avg_noise_size, 12.0, "Avg. noise blob length", this->params()), INT_MEMBER(matcher_permanent_classes_min, 1, "Min # of permanent classes", this->params()), INT_MEMBER(matcher_min_examples_for_prototyping, 3, "Reliable Config Threshold", this->params()), INT_MEMBER(matcher_sufficient_examples_for_prototyping, 5, "Enable adaption even if the ambiguities have not been seen", this->params()), double_MEMBER(matcher_clustering_max_angle_delta, 0.015, "Maximum angle delta for prototype clustering", this->params()), double_MEMBER(classify_misfit_junk_penalty, 0.0, "Penalty to apply when a non-alnum is vertically out of " "its expected textline position", this->params()), double_MEMBER(rating_scale, 1.5, "Rating scaling factor", this->params()), double_MEMBER(certainty_scale, 20.0, "Certainty scaling factor", this->params()), double_MEMBER(tessedit_class_miss_scale, 0.00390625, "Scale factor for features not used", this->params()), INT_MEMBER(classify_adapt_proto_threshold, 230, "Threshold for good protos during adaptive 0-255", this->params()), INT_MEMBER(classify_adapt_feature_threshold, 230, "Threshold for good features during adaptive 0-255", this->params()), BOOL_MEMBER(disable_character_fragments, TRUE, "Do not include character fragments in the" " results of the classifier", this->params()), double_MEMBER(classify_character_fragments_garbage_certainty_threshold, -3.0, "Exclude fragments that do not look like whole" " characters from training and adaption", this->params()), BOOL_MEMBER(classify_debug_character_fragments, FALSE, "Bring up graphical debugging windows for fragments training", this->params()), BOOL_MEMBER(matcher_debug_separate_windows, FALSE, "Use two different windows for debugging the matching: " "One for the protos and one for the features.", this->params()), STRING_MEMBER(classify_learn_debug_str, "", "Class str to debug learning", this->params()), INT_MEMBER(classify_class_pruner_threshold, 229, "Class Pruner Threshold 0-255", this->params()), INT_MEMBER(classify_class_pruner_multiplier, 30, "Class Pruner Multiplier 0-255: ", this->params()), INT_MEMBER(classify_cp_cutoff_strength, 7, "Class Pruner CutoffStrength: ", this->params()), INT_MEMBER(classify_integer_matcher_multiplier, 14, "Integer Matcher Multiplier 0-255: ", this->params()), EnableLearning(true), INT_MEMBER(il1_adaption_test, 0, "Dont adapt to i/I at beginning of word", this->params()), BOOL_MEMBER(classify_bln_numeric_mode, 0, "Assume the input is numbers [0-9].", this->params()), shape_table_(NULL), dict_(&image_) { fontinfo_table_.set_compare_callback( NewPermanentTessCallback(CompareFontInfo)); fontinfo_table_.set_clear_callback( NewPermanentTessCallback(FontInfoDeleteCallback)); fontset_table_.set_compare_callback( NewPermanentTessCallback(CompareFontSet)); fontset_table_.set_clear_callback( NewPermanentTessCallback(FontSetDeleteCallback)); AdaptedTemplates = NULL; PreTrainedTemplates = NULL; AllProtosOn = NULL; PrunedProtos = NULL; AllConfigsOn = NULL; AllProtosOff = NULL; AllConfigsOff = NULL; TempProtoMask = NULL; NormProtos = NULL; AdaptiveMatcherCalls = 0; BaselineClassifierCalls = 0; CharNormClassifierCalls = 0; AmbigClassifierCalls = 0; NumWordsAdaptedTo = 0; NumCharsAdaptedTo = 0; NumBaselineClassesTried = 0; NumCharNormClassesTried = 0; NumAmbigClassesTried = 0; NumClassesOutput = 0; NumAdaptationsFailed = 0; FeaturesHaveBeenExtracted = false; FeaturesOK = true; learn_debug_win_ = NULL; learn_fragmented_word_debug_win_ = NULL; learn_fragments_debug_win_ = NULL; CharNormCutoffs = new uinT16[MAX_NUM_CLASSES]; BaselineCutoffs = new uinT16[MAX_NUM_CLASSES]; }
| tesseract::Classify::~Classify | ( | ) | [virtual] |
Definition at line 173 of file classify.cpp.
{
EndAdaptiveClassifier();
delete learn_debug_win_;
delete learn_fragmented_word_debug_win_;
delete learn_fragments_debug_win_;
delete[] CharNormCutoffs;
delete[] BaselineCutoffs;
}
| int tesseract::Classify::AdaptableWord | ( | TWERD * | Word, |
| const WERD_CHOICE & | BestChoiceWord, | ||
| const WERD_CHOICE & | RawChoiceWord | ||
| ) |
Return TRUE if the specified word is acceptable for adaptation.
Globals: none
| Word | current word |
| BestChoiceWord | best overall choice for word with context |
| RawChoiceWord | best choice for word without context |
Definition at line 896 of file adaptmatch.cpp.
{
int BestChoiceLength = BestChoiceWord.length();
float adaptable_score =
getDict().segment_penalty_dict_case_ok + ADAPTABLE_WERD_ADJUSTMENT;
return // rules that apply in general - simplest to compute first
BestChoiceLength > 0 &&
BestChoiceLength == Word->NumBlobs() &&
BestChoiceLength <= MAX_ADAPTABLE_WERD_SIZE &&
getDict().CurrentBestChoiceAdjustFactor() <= adaptable_score &&
getDict().AlternativeChoicesWorseThan(adaptable_score) &&
getDict().CurrentBestChoiceIs(BestChoiceWord);
}
| void tesseract::Classify::AdaptiveClassifier | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| BLOB_CHOICE_LIST * | Choices, | ||
| CLASS_PRUNER_RESULTS | CPResults | ||
| ) |
This routine calls the adaptive matcher which returns (in an array) the class id of each class matched.
It also returns the number of classes matched. For each class matched it places the best rating found for that class into the Ratings array.
Bad matches are then removed so that they don't need to be sorted. The remaining good matches are then sorted and converted to choices.
This routine also performs some simple speckle filtering.
| Blob | blob to be classified | |
| denorm | normalization/denormalization parameters | |
| [out] | Choices | List of choices found by adaptive matcher. |
| [out] | CPResults | Array of CPResultStruct of size MAX_NUM_CLASSES is filled on return with the choices found by the class pruner and the ratings therefrom. Also contains the detailed results of the integer matcher. |
Definition at line 178 of file adaptmatch.cpp.
{
assert(Choices != NULL);
ADAPT_RESULTS *Results = new ADAPT_RESULTS();
if (AdaptedTemplates == NULL)
AdaptedTemplates = NewAdaptedTemplates (true);
Results->Initialize();
DoAdaptiveMatch(Blob, denorm, Results);
if (CPResults != NULL)
memcpy(CPResults, Results->CPResults,
sizeof(CPResults[0]) * Results->NumMatches);
RemoveBadMatches(Results);
qsort((void *)Results->match, Results->NumMatches,
sizeof(ScoredClass), CompareByRating);
RemoveExtraPuncs(Results);
ConvertMatchesToChoices(denorm, Blob->bounding_box(), Results, Choices);
if (matcher_debug_level >= 1) {
cprintf ("AD Matches = ");
PrintAdaptiveMatchResults(stdout, Results);
}
if (LargeSpeckle(Blob))
AddLargeSpeckleTo(Choices);
#ifndef GRAPHICS_DISABLED
if (classify_enable_adaptive_debugger)
DebugAdaptiveClassifier(Blob, denorm, Results);
#endif
NumClassesOutput += Choices->length();
if (Choices->length() == 0) {
if (!classify_bln_numeric_mode)
tprintf ("Empty classification!\n"); // Should never normally happen.
Choices = new BLOB_CHOICE_LIST();
BLOB_CHOICE_IT temp_it;
temp_it.set_to_list(Choices);
temp_it.add_to_end(
new BLOB_CHOICE(0, 50.0f, -20.0f, -1, -1, NULL, 0, 0, false));
}
delete Results;
} /* AdaptiveClassifier */
| bool tesseract::Classify::AdaptiveClassifierIsFull | ( | ) | [inline] |
Definition at line 319 of file classify.h.
{ return NumAdaptationsFailed > 0; }
| void tesseract::Classify::AdaptToChar | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| CLASS_ID | ClassId, | ||
| int | FontinfoId, | ||
| FLOAT32 | Threshold | ||
| ) |
| Blob | blob to add to templates for ClassId |
| denorm | normalization/denormalization parameters |
| ClassId | class to add blob to |
| FontinfoId | font information from pre-trained templates |
| Threshold | minimum match rating to existing template |
Globals:
Definition at line 928 of file adaptmatch.cpp.
{
int NumFeatures;
INT_FEATURE_ARRAY IntFeatures;
INT_RESULT_STRUCT IntResult;
INT_CLASS IClass;
ADAPT_CLASS Class;
TEMP_CONFIG TempConfig;
FEATURE_SET FloatFeatures;
int NewTempConfigId;
ResetFeaturesHaveBeenExtracted();
NumCharsAdaptedTo++;
if (!LegalClassId (ClassId))
return;
Class = AdaptedTemplates->Class[ClassId];
assert(Class != NULL);
if (IsEmptyAdaptedClass(Class)) {
InitAdaptedClass(Blob, denorm, ClassId, FontinfoId, Class,
AdaptedTemplates);
}
else {
IClass = ClassForClassId (AdaptedTemplates->Templates, ClassId);
NumFeatures = GetAdaptiveFeatures(Blob, IntFeatures, &FloatFeatures);
if (NumFeatures <= 0)
return;
im_.SetBaseLineMatch();
// Only match configs with the matching font.
BIT_VECTOR MatchingFontConfigs = NewBitVector(MAX_NUM_PROTOS);
for (int cfg = 0; cfg < IClass->NumConfigs; ++cfg) {
if (GetFontinfoId(Class, cfg) == FontinfoId) {
SET_BIT(MatchingFontConfigs, cfg);
} else {
reset_bit(MatchingFontConfigs, cfg);
}
}
im_.Match(IClass, AllProtosOn, MatchingFontConfigs,
NumFeatures, IntFeatures,
&IntResult, classify_adapt_feature_threshold,
NO_DEBUG, matcher_debug_separate_windows);
FreeBitVector(MatchingFontConfigs);
SetAdaptiveThreshold(Threshold);
if (IntResult.Rating <= Threshold) {
if (ConfigIsPermanent (Class, IntResult.Config)) {
if (classify_learning_debug_level >= 1)
cprintf ("Found good match to perm config %d = %4.1f%%.\n",
IntResult.Config, (1.0 - IntResult.Rating) * 100.0);
FreeFeatureSet(FloatFeatures);
return;
}
TempConfig = TempConfigFor (Class, IntResult.Config);
IncreaseConfidence(TempConfig);
if (TempConfig->NumTimesSeen > Class->MaxNumTimesSeen) {
Class->MaxNumTimesSeen = TempConfig->NumTimesSeen;
}
if (classify_learning_debug_level >= 1)
cprintf ("Increasing reliability of temp config %d to %d.\n",
IntResult.Config, TempConfig->NumTimesSeen);
if (TempConfigReliable(ClassId, TempConfig)) {
MakePermanent(AdaptedTemplates, ClassId, IntResult.Config, denorm,
Blob);
UpdateAmbigsGroup(ClassId, denorm, Blob);
}
}
else {
if (classify_learning_debug_level >= 1) {
cprintf ("Found poor match to temp config %d = %4.1f%%.\n",
IntResult.Config, (1.0 - IntResult.Rating) * 100.0);
if (classify_learning_debug_level > 2)
DisplayAdaptedChar(Blob, denorm, IClass);
}
NewTempConfigId = MakeNewTemporaryConfig(AdaptedTemplates,
ClassId,
FontinfoId,
NumFeatures,
IntFeatures,
FloatFeatures);
if (NewTempConfigId >= 0 &&
TempConfigReliable(ClassId, TempConfigFor(Class, NewTempConfigId))) {
MakePermanent(AdaptedTemplates, ClassId, NewTempConfigId, denorm, Blob);
UpdateAmbigsGroup(ClassId, denorm, Blob);
}
#ifndef GRAPHICS_DISABLED
if (classify_learning_debug_level > 1) {
DisplayAdaptedChar(Blob, denorm, IClass);
}
#endif
}
FreeFeatureSet(FloatFeatures);
}
} /* AdaptToChar */
| void tesseract::Classify::AdaptToPunc | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| CLASS_ID | ClassId, | ||
| int | FontinfoId, | ||
| FLOAT32 | Threshold | ||
| ) |
| Blob | blob to add to templates for ClassId |
| denorm | normalization/denormalization parameters |
| ClassId | class to add blob to |
| FontinfoId | font information from pre-trained teamples |
| Threshold | minimum match rating to existing template |
Globals:
Definition at line 1077 of file adaptmatch.cpp.
{
ADAPT_RESULTS *Results = new ADAPT_RESULTS();
int i;
Results->Initialize();
CharNormClassifier(Blob, denorm, PreTrainedTemplates, Results);
RemoveBadMatches(Results);
if (Results->NumMatches != 1) {
if (classify_learning_debug_level >= 1) {
cprintf ("Rejecting punc = %s (Alternatives = ",
unicharset.id_to_unichar(ClassId));
for (i = 0; i < Results->NumMatches; i++)
tprintf("%s", unicharset.id_to_unichar(Results->match[i].unichar_id));
tprintf(")\n");
}
} else {
#ifndef SECURE_NAMES
if (classify_learning_debug_level >= 1)
cprintf ("Adapting to punc = %s, thr= %g\n",
unicharset.id_to_unichar(ClassId), Threshold);
#endif
AdaptToChar(Blob, denorm, ClassId, FontinfoId, Threshold);
}
delete Results;
} /* AdaptToPunc */
| void tesseract::Classify::AddNewResult | ( | ADAPT_RESULTS * | results, |
| CLASS_ID | class_id, | ||
| int | shape_id, | ||
| FLOAT32 | rating, | ||
| bool | adapted, | ||
| int | config, | ||
| int | fontinfo_id, | ||
| int | fontinfo_id2 | ||
| ) |
This routine adds the result of a classification into Results. If the new rating is much worse than the current best rating, it is not entered into results because it would end up being stripped later anyway. If the new rating is better than the old rating for the class, it replaces the old rating. If this is the first rating for the class, the class is added to the list of matched classes in Results. If the new rating is better than the best so far, it becomes the best so far.
Globals:
| [out] | results | results to add new result to |
| class_id | class of new result | |
| shape_id | shape index | |
| rating | rating of new result | |
| adapted | adapted match or not | |
| config | config id of new result | |
| fontinfo_id | font information of the new result | |
| fontinfo_id2 | font information of the 2nd choice result |
Definition at line 1137 of file adaptmatch.cpp.
{
ScoredClass *old_match = FindScoredUnichar(results, class_id);
ScoredClass match =
{ class_id,
shape_id,
rating,
adapted,
static_cast<inT16>(config),
static_cast<inT16>(fontinfo_id),
static_cast<inT16>(fontinfo_id2) };
if (rating > results->best_match.rating + matcher_bad_match_pad ||
(old_match && rating >= old_match->rating))
return;
if (!unicharset.get_fragment(class_id))
results->HasNonfragment = true;
if (old_match)
old_match->rating = rating;
else
results->match[results->NumMatches++] = match;
if (rating < results->best_match.rating &&
// Ensure that fragments do not affect best rating, class and config.
// This is needed so that at least one non-fragmented character is
// always present in the results.
// TODO(daria): verify that this helps accuracy and does not
// hurt performance.
!unicharset.get_fragment(class_id)) {
results->best_match = match;
}
} /* AddNewResult */
| void tesseract::Classify::AmbigClassifier | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| INT_TEMPLATES | Templates, | ||
| ADAPT_CLASS * | Classes, | ||
| UNICHAR_ID * | Ambiguities, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
This routine is identical to CharNormClassifier() except that it does no class pruning. It simply matches the unknown blob against the classes listed in Ambiguities.
Globals:
| Blob | blob to be classified | |
| denorm | normalization/denormalization parameters | |
| Templates | built-in templates to classify against | |
| Classes | adapted class templates | |
| Ambiguities | array of class id's to match against | |
| [out] | Results | place to put match results |
Definition at line 1200 of file adaptmatch.cpp.
{
int NumFeatures;
INT_FEATURE_ARRAY IntFeatures;
uinT8* CharNormArray = new uinT8[unicharset.size()];
INT_RESULT_STRUCT IntResult;
CLASS_ID ClassId;
AmbigClassifierCalls++;
NumFeatures = GetCharNormFeatures(Blob, denorm, Templates, IntFeatures,
NULL, CharNormArray,
&(Results->BlobLength), NULL);
if (NumFeatures <= 0) {
delete [] CharNormArray;
return;
}
bool debug = matcher_debug_level >= 2 || classify_debug_level > 1;
if (debug)
tprintf("AM Matches = ");
int top = Blob->bounding_box().top();
int bottom = Blob->bounding_box().bottom();
while (*Ambiguities >= 0) {
ClassId = *Ambiguities;
im_.SetCharNormMatch(classify_integer_matcher_multiplier);
im_.Match(ClassForClassId(Templates, ClassId),
AllProtosOn, AllConfigsOn,
NumFeatures, IntFeatures,
&IntResult,
classify_adapt_feature_threshold, NO_DEBUG,
matcher_debug_separate_windows);
ExpandShapesAndApplyCorrections(NULL, debug, ClassId, bottom, top, 0,
Results->BlobLength, CharNormArray,
IntResult, Results);
Ambiguities++;
NumAmbigClassesTried++;
}
delete [] CharNormArray;
} /* AmbigClassifier */
| UNICHAR_ID * tesseract::Classify::BaselineClassifier | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| ADAPT_TEMPLATES | Templates, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
This routine extracts baseline normalized features from the unknown character and matches them against the specified set of templates. The classes which match are added to Results.
Globals:
| Blob | blob to be classified |
| denorm | normalization/denormalization parameters |
| Templates | current set of adapted templates |
| Results | place to put match results |
Definition at line 1418 of file adaptmatch.cpp.
{
int NumFeatures;
int NumClasses;
INT_FEATURE_ARRAY IntFeatures;
uinT8* CharNormArray = new uinT8[unicharset.size()];
CLASS_ID ClassId;
BaselineClassifierCalls++;
NumFeatures = GetBaselineFeatures(
Blob, denorm, Templates->Templates, IntFeatures, CharNormArray,
&(Results->BlobLength));
if (NumFeatures <= 0) {
delete [] CharNormArray;
return NULL;
}
NumClasses = PruneClasses(Templates->Templates, NumFeatures, IntFeatures,
CharNormArray, BaselineCutoffs, Results->CPResults);
NumBaselineClassesTried += NumClasses;
if (matcher_debug_level >= 2 || classify_debug_level > 1)
cprintf ("BL Matches = ");
im_.SetBaseLineMatch();
MasterMatcher(Templates->Templates, NumFeatures, IntFeatures, CharNormArray,
Templates->Class, matcher_debug_flags, NumClasses,
Blob->bounding_box(), Results->CPResults, Results);
delete [] CharNormArray;
ClassId = Results->best_match.unichar_id;
if (ClassId == NO_CLASS)
return (NULL);
/* this is a bug - maybe should return "" */
return Templates->Class[ClassId]->
Config[Results->best_match.config].Perm->Ambigs;
} /* BaselineClassifier */
| int tesseract::Classify::CharNormClassifier | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| INT_TEMPLATES | Templates, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
This routine extracts character normalized features from the unknown character and matches them against the specified set of templates. The classes which match are added to Results.
| Blob | blob to be classified |
| denorm | normalization/denormalization parameters |
| Templates | templates to classify unknown against |
| Results | place to put match results |
Globals:
Definition at line 1482 of file adaptmatch.cpp.
{
int NumFeatures;
int NumClasses;
INT_FEATURE_ARRAY IntFeatures;
CharNormClassifierCalls++;
uinT8* CharNormArray = new uinT8[unicharset.size()];
int num_pruner_classes = MAX(unicharset.size(),
PreTrainedTemplates->NumClasses);
uinT8* PrunerNormArray = new uinT8[num_pruner_classes];
NumFeatures = GetCharNormFeatures(Blob, denorm, Templates, IntFeatures,
PrunerNormArray, CharNormArray,
&(Results->BlobLength), NULL);
if (NumFeatures <= 0) {
delete [] CharNormArray;
delete [] PrunerNormArray;
return 0;
}
NumClasses = PruneClasses(Templates, NumFeatures, IntFeatures,
PrunerNormArray,
shape_table_ != NULL ? &shapetable_cutoffs_[0]
: CharNormCutoffs,
Results->CPResults);
if (tessedit_single_match && NumClasses > 1)
NumClasses = 1;
NumCharNormClassesTried += NumClasses;
im_.SetCharNormMatch(classify_integer_matcher_multiplier);
MasterMatcher(Templates, NumFeatures, IntFeatures, CharNormArray,
NULL, matcher_debug_flags, NumClasses,
Blob->bounding_box(), Results->CPResults, Results);
delete [] CharNormArray;
delete [] PrunerNormArray;
return NumFeatures;
} /* CharNormClassifier */
| int tesseract::Classify::CharNormTrainingSample | ( | bool | pruner_only, |
| const TrainingSample & | sample, | ||
| GenericVector< ShapeRating > * | results | ||
| ) |
Definition at line 1526 of file adaptmatch.cpp.
{
results->clear();
ADAPT_RESULTS* adapt_results = new ADAPT_RESULTS();
adapt_results->Initialize();
// Compute the bounding box of the features.
int num_features = sample.num_features();
TBOX blob_box;
for (int f = 0; f < num_features; ++f) {
const INT_FEATURE_STRUCT feature = sample.features()[f];
TBOX fbox(feature.X, feature.Y, feature.X, feature.Y);
blob_box += fbox;
}
// Compute the char_norm_array from the saved cn_feature.
FEATURE norm_feature = NewFeature(&CharNormDesc);
norm_feature->Params[CharNormY] = sample.cn_feature(CharNormY);
norm_feature->Params[CharNormLength] = sample.cn_feature(CharNormLength);
norm_feature->Params[CharNormRx] = sample.cn_feature(CharNormRx);
norm_feature->Params[CharNormRy] = sample.cn_feature(CharNormRy);
uinT8* char_norm_array = new uinT8[unicharset.size()];
int num_pruner_classes = MAX(unicharset.size(),
PreTrainedTemplates->NumClasses);
uinT8* pruner_norm_array = new uinT8[num_pruner_classes];
adapt_results->BlobLength =
static_cast<int>(ActualOutlineLength(norm_feature) * 20 + 0.5);
ComputeCharNormArrays(norm_feature, PreTrainedTemplates, char_norm_array,
pruner_norm_array);
int num_classes = PruneClasses(PreTrainedTemplates, num_features,
sample.features(),
pruner_norm_array,
shape_table_ != NULL ? &shapetable_cutoffs_[0]
: CharNormCutoffs,
adapt_results->CPResults);
delete [] pruner_norm_array;
if (pruner_only) {
// Convert pruner results to output format.
for (int i = 0; i < num_classes; ++i) {
int class_id = adapt_results->CPResults[i].Class;
int shape_id = class_id;
if (shape_table_ != NULL) {
// All shapes in a class have the same combination of unichars, so
// it doesn't really matter which config we give it, as we aren't
// trying to get the font here.
shape_id = ClassAndConfigIDToFontOrShapeID(class_id, 0);
}
results->push_back(
ShapeRating(shape_id, 1.0f - adapt_results->CPResults[i].Rating));
}
} else {
im_.SetCharNormMatch(classify_integer_matcher_multiplier);
MasterMatcher(PreTrainedTemplates, num_features, sample.features(),
char_norm_array,
NULL, matcher_debug_flags, num_classes,
blob_box, adapt_results->CPResults, adapt_results);
// Convert master matcher results to output format.
for (int i = 0; i < adapt_results->NumMatches; i++) {
ScoredClass next = adapt_results->match[i];
results->push_back(ShapeRating(next.shape_id, 1.0f - next.rating));
}
results->sort(&ShapeRating::SortDescendingRating);
}
delete [] char_norm_array;
delete adapt_results;
return num_features;
} /* CharNormTrainingSample */
| int tesseract::Classify::ClassAndConfigIDToFontOrShapeID | ( | int | class_id, |
| int | int_result_config | ||
| ) | const |
Definition at line 2734 of file adaptmatch.cpp.
{
int font_set_id = PreTrainedTemplates->Class[class_id]->font_set_id;
// Older inttemps have no font_ids.
if (font_set_id < 0)
return kBlankFontinfoId;
const FontSet &fs = fontset_table_.get(font_set_id);
ASSERT_HOST(int_result_config >= 0 && int_result_config < fs.size);
return fs.configs[int_result_config];
}
| STRING tesseract::Classify::ClassIDToDebugStr | ( | const INT_TEMPLATES_STRUCT * | templates, |
| int | class_id, | ||
| int | config_id | ||
| ) | const |
Definition at line 2721 of file adaptmatch.cpp.
{
STRING class_string;
if (templates == PreTrainedTemplates && shape_table_ != NULL) {
int shape_id = ClassAndConfigIDToFontOrShapeID(class_id, config_id);
class_string = shape_table_->DebugStr(shape_id);
} else {
class_string = unicharset.debug_str(class_id);
}
return class_string;
}
| void tesseract::Classify::ClassifyAsNoise | ( | ADAPT_RESULTS * | Results | ) |
This routine computes a rating which reflects the likelihood that the blob being classified is a noise blob. NOTE: assumes that the blob length has already been computed and placed into Results.
| Results | results to add noise classification to |
Globals:
Definition at line 1610 of file adaptmatch.cpp.
{
register FLOAT32 Rating;
Rating = Results->BlobLength / matcher_avg_noise_size;
Rating *= Rating;
Rating /= 1.0 + Rating;
AddNewResult(Results, NO_CLASS, -1, Rating, false, -1,
kBlankFontinfoId, kBlankFontinfoId);
} /* ClassifyAsNoise */
| void tesseract::Classify::ClearCharNormArray | ( | uinT8 * | char_norm_array | ) |
For each class in the unicharset, clears the corresponding entry in char_norm_array. char_norm_array is indexed by unichar_id.
Globals:
| char_norm_array | array to be cleared |
Definition at line 48 of file float2int.cpp.
{
memset(char_norm_array, 0, sizeof(*char_norm_array) * unicharset.size());
} /* ClearCharNormArray */
| void tesseract::Classify::ComputeCharNormArrays | ( | FEATURE_STRUCT * | norm_feature, |
| INT_TEMPLATES_STRUCT * | templates, | ||
| uinT8 * | char_norm_array, | ||
| uinT8 * | pruner_array | ||
| ) |
Definition at line 2087 of file adaptmatch.cpp.
{
ComputeIntCharNormArray(*norm_feature, char_norm_array);
if (pruner_array != NULL) {
if (shape_table_ == NULL) {
ComputeIntCharNormArray(*norm_feature, pruner_array);
} else {
memset(pruner_array, MAX_UINT8,
templates->NumClasses * sizeof(pruner_array[0]));
// Each entry in the pruner norm array is the MIN of all the entries of
// the corresponding unichars in the CharNormArray.
for (int id = 0; id < templates->NumClasses; ++id) {
int font_set_id = templates->Class[id]->font_set_id;
const FontSet &fs = fontset_table_.get(font_set_id);
for (int config = 0; config < fs.size; ++config) {
const Shape& shape = shape_table_->GetShape(fs.configs[config]);
for (int c = 0; c < shape.size(); ++c) {
if (char_norm_array[shape[c].unichar_id] < pruner_array[id])
pruner_array[id] = char_norm_array[shape[c].unichar_id];
}
}
}
}
}
FreeFeature(norm_feature);
}
| double tesseract::Classify::ComputeCorrectedRating | ( | bool | debug, |
| int | unichar_id, | ||
| double | cp_rating, | ||
| double | im_rating, | ||
| int | feature_misses, | ||
| int | bottom, | ||
| int | top, | ||
| int | blob_length, | ||
| const uinT8 * | cn_factors | ||
| ) |
Definition at line 1355 of file adaptmatch.cpp.
{
// Compute class feature corrections.
double cn_corrected = im_.ApplyCNCorrection(im_rating, blob_length,
cn_factors[unichar_id]);
double miss_penalty = tessedit_class_miss_scale * feature_misses;
double vertical_penalty = 0.0;
// Penalize non-alnums for being vertical misfits.
if (!unicharset.get_isalpha(unichar_id) &&
!unicharset.get_isdigit(unichar_id) &&
cn_factors[unichar_id] != 0 && classify_misfit_junk_penalty > 0.0) {
int min_bottom, max_bottom, min_top, max_top;
unicharset.get_top_bottom(unichar_id, &min_bottom, &max_bottom,
&min_top, &max_top);
if (debug) {
tprintf("top=%d, vs [%d, %d], bottom=%d, vs [%d, %d]\n",
top, min_top, max_top, bottom, min_bottom, max_bottom);
}
if (top < min_top || top > max_top ||
bottom < min_bottom || bottom > max_bottom) {
vertical_penalty = classify_misfit_junk_penalty;
}
}
double result =cn_corrected + miss_penalty + vertical_penalty;
if (result > WORST_POSSIBLE_RATING)
result = WORST_POSSIBLE_RATING;
if (debug) {
tprintf("%s: %2.1f(CP%2.1f, IM%2.1f + CN%.2f(%d) + MP%2.1f + VP%2.1f)\n",
unicharset.id_to_unichar(unichar_id),
result * 100.0,
cp_rating * 100.0,
im_rating * 100.0,
(cn_corrected - im_rating) * 100.0,
cn_factors[unichar_id],
miss_penalty * 100.0,
vertical_penalty * 100.0);
}
return result;
}
| void tesseract::Classify::ComputeIntCharNormArray | ( | const FEATURE_STRUCT & | norm_feature, |
| uinT8 * | char_norm_array | ||
| ) |
For each class in unicharset, computes the match between norm_feature and the normalization protos for that class. Converts this number to the range from 0 - 255 and stores it into char_norm_array. CharNormArray is indexed by unichar_id.
Globals:
| norm_feature | character normalization feature | |
| [out] | char_norm_array | place to put results of size unicharset.size() |
Definition at line 69 of file float2int.cpp.
{
for (int i = 0; i < unicharset.size(); i++) {
int norm_adjust = static_cast<int>(INT_CHAR_NORM_RANGE *
ComputeNormMatch(i, norm_feature, FALSE));
char_norm_array[i] = ClipToRange(norm_adjust, 0, MAX_INT_CHAR_NORM);
}
} /* ComputeIntCharNormArray */
| void tesseract::Classify::ComputeIntFeatures | ( | FEATURE_SET | Features, |
| INT_FEATURE_ARRAY | IntFeatures | ||
| ) |
This routine converts each floating point pico-feature in Features into integer format and saves it into IntFeatures.
Globals:
| Features | floating point pico-features to be converted | |
| [out] | IntFeatures | array to put converted features into |
Definition at line 94 of file float2int.cpp.
{
int Fid;
FEATURE Feature;
FLOAT32 YShift;
if (classify_norm_method == baseline)
YShift = BASELINE_Y_SHIFT;
else
YShift = Y_SHIFT;
for (Fid = 0; Fid < Features->NumFeatures; Fid++) {
Feature = Features->Features[Fid];
IntFeatures[Fid].X = BucketFor (Feature->Params[PicoFeatX],
X_SHIFT, INT_FEAT_RANGE);
IntFeatures[Fid].Y = BucketFor (Feature->Params[PicoFeatY],
YShift, INT_FEAT_RANGE);
IntFeatures[Fid].Theta = CircBucketFor (Feature->Params[PicoFeatDir],
ANGLE_SHIFT, INT_FEAT_RANGE);
IntFeatures[Fid].CP_misses = 0;
}
} /* ComputeIntFeatures */
| FLOAT32 tesseract::Classify::ComputeNormMatch | ( | CLASS_ID | ClassId, |
| const FEATURE_STRUCT & | feature, | ||
| BOOL8 | DebugMatch | ||
| ) |
Definition at line 73 of file normmatch.cpp.
{
/*
** Parameters:
** ClassId id of class to match against
** Feature character normalization feature
** DebugMatch controls dump of debug info
** Globals:
** NormProtos character normalization prototypes
** Operation: This routine compares Features against each character
** normalization proto for ClassId and returns the match
** rating of the best match.
** Return: Best match rating for Feature against protos of ClassId.
** Exceptions: none
** History: Wed Dec 19 16:56:12 1990, DSJ, Created.
*/
LIST Protos;
FLOAT32 BestMatch;
FLOAT32 Match;
FLOAT32 Delta;
PROTOTYPE *Proto;
int ProtoId;
/* handle requests for classification as noise */
if (ClassId == NO_CLASS) {
/* kludge - clean up constants and make into control knobs later */
Match = (feature.Params[CharNormLength] *
feature.Params[CharNormLength] * 500.0 +
feature.Params[CharNormRx] *
feature.Params[CharNormRx] * 8000.0 +
feature.Params[CharNormRy] *
feature.Params[CharNormRy] * 8000.0);
return (1.0 - NormEvidenceOf (Match));
}
BestMatch = MAX_FLOAT32;
Protos = NormProtos->Protos[ClassId];
if (DebugMatch) {
tprintf("\nChar norm for class %s\n", unicharset.id_to_unichar(ClassId));
}
ProtoId = 0;
iterate(Protos) {
Proto = (PROTOTYPE *) first_node (Protos);
Delta = feature.Params[CharNormY] - Proto->Mean[CharNormY];
Match = Delta * Delta * Proto->Weight.Elliptical[CharNormY];
if (DebugMatch) {
tprintf("YMiddle: Proto=%g, Delta=%g, Var=%g, Dist=%g\n",
Proto->Mean[CharNormY], Delta,
Proto->Weight.Elliptical[CharNormY], Match);
}
Delta = feature.Params[CharNormRx] - Proto->Mean[CharNormRx];
Match += Delta * Delta * Proto->Weight.Elliptical[CharNormRx];
if (DebugMatch) {
tprintf("Height: Proto=%g, Delta=%g, Var=%g, Dist=%g\n",
Proto->Mean[CharNormRx], Delta,
Proto->Weight.Elliptical[CharNormRx], Match);
}
// Ry is width! See intfx.cpp.
Delta = feature.Params[CharNormRy] - Proto->Mean[CharNormRy];
if (DebugMatch) {
tprintf("Width: Proto=%g, Delta=%g, Var=%g\n",
Proto->Mean[CharNormRy], Delta,
Proto->Weight.Elliptical[CharNormRy]);
}
Delta = Delta * Delta * Proto->Weight.Elliptical[CharNormRy];
Delta *= kWidthErrorWeighting;
Match += Delta;
if (DebugMatch) {
tprintf("Total Dist=%g, scaled=%g, sigmoid=%g, penalty=%g\n",
Match, Match / classify_norm_adj_midpoint,
NormEvidenceOf(Match), 256 * (1 - NormEvidenceOf(Match)));
}
if (Match < BestMatch)
BestMatch = Match;
ProtoId++;
}
return 1.0 - NormEvidenceOf(BestMatch);
} /* ComputeNormMatch */
| void tesseract::Classify::ConvertMatchesToChoices | ( | const DENORM & | denorm, |
| const TBOX & | box, | ||
| ADAPT_RESULTS * | Results, | ||
| BLOB_CHOICE_LIST * | Choices | ||
| ) |
The function converts the given match ratings to the list of blob choices with ratings and certainties (used by the context checkers). If character fragments are present in the results, this function also makes sure that there is at least one non-fragmented classification included. For each classification result check the unicharset for "definite" ambiguities and modify the resulting Choices accordingly.
Definition at line 1670 of file adaptmatch.cpp.
{
assert(Choices != NULL);
FLOAT32 Rating;
FLOAT32 Certainty;
BLOB_CHOICE_IT temp_it;
bool contains_nonfrag = false;
temp_it.set_to_list(Choices);
int choices_length = 0;
// With no shape_table_ maintain the previous MAX_MATCHES as the maximum
// number of returned results, but with a shape_table_ we want to have room
// for at least the biggest shape (which might contain hundreds of Indic
// grapheme fragments) and more, so use double the size of the biggest shape
// if that is more than the default.
int max_matches = MAX_MATCHES;
if (shape_table_ != NULL) {
max_matches = shape_table_->MaxNumUnichars() * 2;
if (max_matches < MAX_MATCHES)
max_matches = MAX_MATCHES;
}
for (int i = 0; i < Results->NumMatches; i++) {
ScoredClass next = Results->match[i];
int fontinfo_id = next.fontinfo_id;
int fontinfo_id2 = next.fontinfo_id2;
bool adapted = next.adapted;
bool current_is_frag = (unicharset.get_fragment(next.unichar_id) != NULL);
if (temp_it.length()+1 == max_matches &&
!contains_nonfrag && current_is_frag) {
continue; // look for a non-fragmented character to fill the
// last spot in Choices if only fragments are present
}
// BlobLength can never be legally 0, this means recognition failed.
// But we must return a classification result because some invoking
// functions (chopper/permuter) do not anticipate a null blob choice.
// So we need to assign a poor, but not infinitely bad score.
if (Results->BlobLength == 0) {
Certainty = -20;
Rating = 100; // should be -certainty * real_blob_length
} else {
Rating = Certainty = next.rating;
Rating *= rating_scale * Results->BlobLength;
Certainty *= -(getDict().certainty_scale);
}
inT16 min_xheight, max_xheight;
denorm.XHeightRange(next.unichar_id, unicharset, box,
&min_xheight, &max_xheight);
temp_it.add_to_end(new BLOB_CHOICE(next.unichar_id, Rating, Certainty,
fontinfo_id, fontinfo_id2,
unicharset.get_script(next.unichar_id),
min_xheight, max_xheight, adapted));
contains_nonfrag |= !current_is_frag; // update contains_nonfrag
choices_length++;
if (choices_length >= max_matches) break;
}
Results->NumMatches = choices_length;
} // ConvertMatchesToChoices
Definition at line 528 of file intproto.cpp.
{
/*
** Parameters:
** Proto floating-pt proto to be converted to integer format
** ProtoId id of proto
** Class integer class to add converted proto to
** Globals: none
** Operation: This routine converts Proto to integer format and
** installs it as ProtoId in Class.
** Return: none
** Exceptions: none
** History: Fri Feb 8 11:22:43 1991, DSJ, Created.
*/
INT_PROTO P;
FLOAT32 Param;
assert(ProtoId < Class->NumProtos);
P = ProtoForProtoId(Class, ProtoId);
Param = Proto->A * 128;
P->A = TruncateParam(Param, -128, 127, NULL);
Param = -Proto->B * 256;
P->B = TruncateParam(Param, 0, 255, NULL);
Param = Proto->C * 128;
P->C = TruncateParam(Param, -128, 127, NULL);
Param = Proto->Angle * 256;
if (Param < 0 || Param >= 256)
P->Angle = 0;
else
P->Angle = (uinT8) Param;
/* round proto length to nearest integer number of pico-features */
Param = (Proto->Length / GetPicoFeatureLength()) + 0.5;
Class->ProtoLengths[ProtoId] = TruncateParam(Param, 1, 255, NULL);
if (classify_learning_debug_level >= 2)
cprintf("Converted ffeat to (A=%d,B=%d,C=%d,L=%d)",
P->A, P->B, P->C, Class->ProtoLengths[ProtoId]);
} /* ConvertProto */
| INT_TEMPLATES tesseract::Classify::CreateIntTemplates | ( | CLASSES | FloatProtos, |
| const UNICHARSET & | target_unicharset | ||
| ) |
Definition at line 573 of file intproto.cpp.
{
/*
** Parameters:
** FloatProtos prototypes in old floating pt format
** Globals: none
** Operation: This routine converts from the old floating point format
** to the new integer format.
** Return: New set of training templates in integer format.
** Exceptions: none
** History: Thu Feb 7 14:40:42 1991, DSJ, Created.
*/
INT_TEMPLATES IntTemplates;
CLASS_TYPE FClass;
INT_CLASS IClass;
int ClassId;
int ProtoId;
int ConfigId;
IntTemplates = NewIntTemplates();
for (ClassId = 0; ClassId < target_unicharset.size(); ClassId++) {
FClass = &(FloatProtos[ClassId]);
if (FClass->NumProtos == 0 && FClass->NumConfigs == 0 &&
strcmp(target_unicharset.id_to_unichar(ClassId), " ") != 0) {
cprintf("Warning: no protos/configs for %s in CreateIntTemplates()\n",
target_unicharset.id_to_unichar(ClassId));
}
assert(UnusedClassIdIn(IntTemplates, ClassId));
IClass = NewIntClass(FClass->NumProtos, FClass->NumConfigs);
FontSet fs;
fs.size = FClass->font_set.size();
fs.configs = new int[fs.size];
for (int i = 0; i < fs.size; ++i) {
fs.configs[i] = FClass->font_set.get(i);
}
if (this->fontset_table_.contains(fs)) {
IClass->font_set_id = this->fontset_table_.get_id(fs);
delete[] fs.configs;
} else {
IClass->font_set_id = this->fontset_table_.push_back(fs);
}
AddIntClass(IntTemplates, ClassId, IClass);
for (ProtoId = 0; ProtoId < FClass->NumProtos; ProtoId++) {
AddIntProto(IClass);
ConvertProto(ProtoIn(FClass, ProtoId), ProtoId, IClass);
AddProtoToProtoPruner(ProtoIn(FClass, ProtoId), ProtoId, IClass,
classify_learning_debug_level >= 2);
AddProtoToClassPruner(ProtoIn(FClass, ProtoId), ClassId, IntTemplates);
}
for (ConfigId = 0; ConfigId < FClass->NumConfigs; ConfigId++) {
AddIntConfig(IClass);
ConvertConfig(FClass->Configurations[ConfigId], ConfigId, IClass);
}
}
return (IntTemplates);
} /* CreateIntTemplates */
| void tesseract::Classify::DebugAdaptiveClassifier | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
| Blob | blob whose classification is being debugged |
| denorm | normalization/denormalization parameters |
| Results | results of match being debugged |
Globals: none
Definition at line 1743 of file adaptmatch.cpp.
{
for (int i = 0; i < Results->NumMatches; i++) {
if (Results->match[i].rating < Results->best_match.rating)
Results->best_match = Results->match[i];
}
const char *Prompt =
"Left-click in IntegerMatch Window to continue or right click to debug...";
CLASS_ID unichar_id = Results->best_match.unichar_id;
int shape_id = Results->best_match.shape_id;
bool adaptive_on = true;
bool pretrained_on = true;
const char* debug_mode;
do {
if (!pretrained_on)
debug_mode = "Adaptive Templates Only";
else if (!adaptive_on)
debug_mode = "PreTrained Templates Only";
else
debug_mode = "All Templates";
ShowMatchDisplay();
tprintf("Debugging class %d = %s in mode %s ...",
unichar_id, unicharset.id_to_unichar(unichar_id), debug_mode);
if (shape_id >= 0 && shape_table_ != NULL) {
tprintf(" from shape %s\n", shape_table_->DebugStr(shape_id).string());
}
ShowBestMatchFor(Blob, denorm, unichar_id, shape_id, adaptive_on,
pretrained_on, Results);
UpdateMatchDisplay();
} while ((unichar_id = GetClassToDebug(Prompt, &adaptive_on,
&pretrained_on, &shape_id)) != 0);
} /* DebugAdaptiveClassifier */
| void tesseract::Classify::DisplayAdaptedChar | ( | TBLOB * | blob, |
| const DENORM & | denorm, | ||
| INT_CLASS_STRUCT * | int_class | ||
| ) |
Definition at line 1031 of file adaptmatch.cpp.
{
#ifndef GRAPHICS_DISABLED
int bloblength = 0;
INT_FEATURE_ARRAY features;
uinT8* norm_array = new uinT8[unicharset.size()];
int num_features = GetBaselineFeatures(blob, denorm, PreTrainedTemplates,
features,
norm_array, &bloblength);
delete [] norm_array;
INT_RESULT_STRUCT IntResult;
im_.Match(int_class, AllProtosOn, AllConfigsOn,
num_features, features,
&IntResult, classify_adapt_feature_threshold,
NO_DEBUG, matcher_debug_separate_windows);
cprintf ("Best match to temp config %d = %4.1f%%.\n",
IntResult.Config, (1.0 - IntResult.Rating) * 100.0);
if (classify_learning_debug_level >= 2) {
uinT32 ConfigMask;
ConfigMask = 1 << IntResult.Config;
ShowMatchDisplay();
im_.Match(int_class, AllProtosOn, (BIT_VECTOR)&ConfigMask,
num_features, features,
&IntResult, classify_adapt_feature_threshold,
6 | 0x19, matcher_debug_separate_windows);
UpdateMatchDisplay();
}
#endif
}
| void tesseract::Classify::DoAdaptiveMatch | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
This routine performs an adaptive classification. If we have not yet adapted to enough classes, a simple classification to the pre-trained templates is performed. Otherwise, we match the blob against the adapted templates. If the adapted templates do not match well, we try a match against the pre-trained templates. If an adapted template match is found, we do a match to any pre-trained templates which could be ambiguous. The results from all of these classifications are merged together into Results.
| Blob | blob to be classified |
| denorm | normalization/denormalization parameters |
| Results | place to put match results |
Globals:
Definition at line 1803 of file adaptmatch.cpp.
{
UNICHAR_ID *Ambiguities;
AdaptiveMatcherCalls++;
InitIntFX();
if (AdaptedTemplates->NumPermClasses < matcher_permanent_classes_min ||
tess_cn_matching) {
CharNormClassifier(Blob, denorm, PreTrainedTemplates, Results);
} else {
Ambiguities = BaselineClassifier(Blob, denorm, AdaptedTemplates, Results);
if ((Results->NumMatches > 0 &&
MarginalMatch (Results->best_match.rating) &&
!tess_bn_matching) ||
Results->NumMatches == 0) {
CharNormClassifier(Blob, denorm, PreTrainedTemplates, Results);
} else if (Ambiguities && *Ambiguities >= 0 && !tess_bn_matching) {
AmbigClassifier(Blob, denorm,
PreTrainedTemplates,
AdaptedTemplates->Class,
Ambiguities,
Results);
}
}
// Force the blob to be classified as noise
// if the results contain only fragments.
// TODO(daria): verify that this is better than
// just adding a NULL classification.
if (!Results->HasNonfragment || Results->NumMatches == 0)
ClassifyAsNoise(Results);
} /* DoAdaptiveMatch */
| void tesseract::Classify::EndAdaptiveClassifier | ( | ) |
This routine performs cleanup operations on the adaptive classifier. It should be called before the program is terminated. Its main function is to save the adapted templates to a file.
Globals:
Definition at line 478 of file adaptmatch.cpp.
{
STRING Filename;
FILE *File;
#ifndef SECURE_NAMES
if (AdaptedTemplates != NULL &&
classify_enable_adaptive_matcher && classify_save_adapted_templates) {
Filename = imagefile + ADAPT_TEMPLATE_SUFFIX;
File = fopen (Filename.string(), "wb");
if (File == NULL)
cprintf ("Unable to save adapted templates to %s!\n", Filename.string());
else {
cprintf ("\nSaving adapted templates to %s ...", Filename.string());
fflush(stdout);
WriteAdaptedTemplates(File, AdaptedTemplates);
cprintf ("\n");
fclose(File);
}
}
#endif
if (AdaptedTemplates != NULL) {
free_adapted_templates(AdaptedTemplates);
AdaptedTemplates = NULL;
}
if (PreTrainedTemplates != NULL) {
free_int_templates(PreTrainedTemplates);
PreTrainedTemplates = NULL;
}
getDict().EndDangerousAmbigs();
FreeNormProtos();
if (AllProtosOn != NULL) {
FreeBitVector(AllProtosOn);
FreeBitVector(PrunedProtos);
FreeBitVector(AllConfigsOn);
FreeBitVector(AllProtosOff);
FreeBitVector(AllConfigsOff);
FreeBitVector(TempProtoMask);
AllProtosOn = NULL;
PrunedProtos = NULL;
AllConfigsOn = NULL;
AllProtosOff = NULL;
AllConfigsOff = NULL;
TempProtoMask = NULL;
}
delete shape_table_;
shape_table_ = NULL;
} /* EndAdaptiveClassifier */
| void tesseract::Classify::ExpandShapesAndApplyCorrections | ( | ADAPT_CLASS * | classes, |
| bool | debug, | ||
| int | class_id, | ||
| int | bottom, | ||
| int | top, | ||
| float | cp_rating, | ||
| int | blob_length, | ||
| const uinT8 * | cn_factors, | ||
| INT_RESULT_STRUCT & | int_result, | ||
| ADAPT_RESULTS * | final_results | ||
| ) |
Definition at line 1290 of file adaptmatch.cpp.
{
// Compute the fontinfo_ids.
int fontinfo_id = kBlankFontinfoId;
int fontinfo_id2 = kBlankFontinfoId;
if (classes != NULL) {
// Adapted result.
fontinfo_id = GetFontinfoId(classes[class_id], int_result.Config);
if (int_result.Config2 >= 0)
fontinfo_id2 = GetFontinfoId(classes[class_id], int_result.Config2);
} else {
// Pre-trained result.
fontinfo_id = ClassAndConfigIDToFontOrShapeID(class_id, int_result.Config);
if (int_result.Config2 >= 0) {
fontinfo_id2 = ClassAndConfigIDToFontOrShapeID(class_id,
int_result.Config2);
}
if (shape_table_ != NULL) {
// Actually fontinfo_id is an index into the shape_table_ and it
// contains a list of unchar_id/font_id pairs.
int shape_id = fontinfo_id;
const Shape& shape = shape_table_->GetShape(fontinfo_id);
double min_rating = 0.0;
for (int c = 0; c < shape.size(); ++c) {
int unichar_id = shape[c].unichar_id;
fontinfo_id = shape[c].font_ids[0];
if (shape[c].font_ids.size() > 1)
fontinfo_id2 = shape[c].font_ids[1];
else if (fontinfo_id2 != kBlankFontinfoId)
fontinfo_id2 = shape_table_->GetShape(fontinfo_id2)[0].font_ids[0];
double rating = ComputeCorrectedRating(debug, unichar_id, cp_rating,
int_result.Rating,
int_result.FeatureMisses,
bottom, top, blob_length,
cn_factors);
if (c == 0 || rating < min_rating)
min_rating = rating;
if (unicharset.get_enabled(unichar_id)) {
AddNewResult(final_results, unichar_id, shape_id, rating,
classes != NULL, int_result.Config,
fontinfo_id, fontinfo_id2);
}
}
int_result.Rating = min_rating;
return;
}
}
double rating = ComputeCorrectedRating(debug, class_id, cp_rating,
int_result.Rating,
int_result.FeatureMisses,
bottom, top, blob_length,
cn_factors);
if (unicharset.get_enabled(class_id)) {
AddNewResult(final_results, class_id, -1, rating,
classes != NULL, int_result.Config,
fontinfo_id, fontinfo_id2);
}
int_result.Rating = rating;
}
| FEATURE_SET tesseract::Classify::ExtractOutlineFeatures | ( | TBLOB * | Blob | ) |
Definition at line 36 of file outfeat.cpp.
{
/*
** Parameters:
** Blob blob to extract pico-features from
** LineStats statistics on text row blob is in
** Globals: none
** Operation: Convert each segment in the outline to a feature
** and return the features.
** Return: Outline-features for Blob.
** Exceptions: none
** History: 11/13/90, DSJ, Created.
** 05/24/91, DSJ, Updated for either char or baseline normalize.
*/
LIST Outlines;
LIST RemainingOutlines;
MFOUTLINE Outline;
FEATURE_SET FeatureSet;
FLOAT32 XScale, YScale;
FeatureSet = NewFeatureSet (MAX_OUTLINE_FEATURES);
if (Blob == NULL)
return (FeatureSet);
Outlines = ConvertBlob (Blob);
NormalizeOutlines(Outlines, &XScale, &YScale);
RemainingOutlines = Outlines;
iterate(RemainingOutlines) {
Outline = (MFOUTLINE) first_node (RemainingOutlines);
ConvertToOutlineFeatures(Outline, FeatureSet);
}
if (classify_norm_method == baseline)
NormalizeOutlineX(FeatureSet);
FreeOutlines(Outlines);
return (FeatureSet);
} /* ExtractOutlineFeatures */
| FEATURE_SET tesseract::Classify::ExtractPicoFeatures | ( | TBLOB * | Blob | ) |
Definition at line 57 of file picofeat.cpp.
{
/*
** Parameters:
** Blob blob to extract pico-features from
** LineStats statistics on text row blob is in
** Globals:
** classify_norm_method normalization method currently specified
** Operation: Dummy for now.
** Return: Pico-features for Blob.
** Exceptions: none
** History: 9/4/90, DSJ, Created.
*/
LIST Outlines;
LIST RemainingOutlines;
MFOUTLINE Outline;
FEATURE_SET FeatureSet;
FLOAT32 XScale, YScale;
FeatureSet = NewFeatureSet(MAX_PICO_FEATURES);
Outlines = ConvertBlob(Blob);
NormalizeOutlines(Outlines, &XScale, &YScale);
RemainingOutlines = Outlines;
iterate(RemainingOutlines) {
Outline = (MFOUTLINE) first_node (RemainingOutlines);
ConvertToPicoFeatures2(Outline, FeatureSet);
}
if (classify_norm_method == baseline)
NormalizePicoX(FeatureSet);
FreeOutlines(Outlines);
return (FeatureSet);
} /* ExtractPicoFeatures */
| void tesseract::Classify::FreeNormProtos | ( | ) |
Definition at line 157 of file normmatch.cpp.
{
if (NormProtos != NULL) {
for (int i = 0; i < NormProtos->NumProtos; i++)
FreeProtoList(&NormProtos->Protos[i]);
Efree(NormProtos->Protos);
Efree(NormProtos->ParamDesc);
Efree(NormProtos);
NormProtos = NULL;
}
}
| UnicityTable<FontInfo>& tesseract::Classify::get_fontinfo_table | ( | ) | [inline] |
Definition at line 336 of file classify.h.
{
return fontinfo_table_;
}
| UnicityTable<FontSet>& tesseract::Classify::get_fontset_table | ( | ) | [inline] |
Definition at line 339 of file classify.h.
{
return fontset_table_;
}
| int tesseract::Classify::GetAdaptiveFeatures | ( | TBLOB * | Blob, |
| INT_FEATURE_ARRAY | IntFeatures, | ||
| FEATURE_SET * | FloatFeatures | ||
| ) |
This routine sets up the feature extractor to extract baseline normalized pico-features.
The extracted pico-features are converted to integer form and placed in IntFeatures. The original floating-pt. features are returned in FloatFeatures.
Globals: none
| Blob | blob to extract features from | |
| [out] | IntFeatures | array to fill with integer features |
| [out] | FloatFeatures | place to return actual floating-pt features |
Definition at line 856 of file adaptmatch.cpp.
{
FEATURE_SET Features;
int NumFeatures;
classify_norm_method.set_value(baseline);
Features = ExtractPicoFeatures(Blob);
NumFeatures = Features->NumFeatures;
if (NumFeatures > UNLIKELY_NUM_FEAT) {
FreeFeatureSet(Features);
return 0;
}
ComputeIntFeatures(Features, IntFeatures);
*FloatFeatures = Features;
return NumFeatures;
} /* GetAdaptiveFeatures */
| void tesseract::Classify::GetAdaptThresholds | ( | TWERD * | Word, |
| const DENORM & | denorm, | ||
| const WERD_CHOICE & | BestChoice, | ||
| const WERD_CHOICE & | BestRawChoice, | ||
| FLOAT32 | Thresholds[] | ||
| ) |
This routine tries to estimate how tight the adaptation threshold should be set for each character in the current word. In general, the routine tries to set tighter thresholds for a character when the current set of templates would have made an error on that character. It tries to set a threshold tight enough to eliminate the error. Two different sets of rules can be used to determine the desired thresholds.
| Word | current word | |
| denorm | normalization/denormalization parameters | |
| BestChoice | best choice for current word with context | |
| BestRawChoice | best choice for current word without context | |
| [out] | Thresholds | array of thresholds to be filled in |
Globals:
Definition at line 1864 of file adaptmatch.cpp.
{
getDict().FindClassifierErrors(matcher_perfect_threshold,
matcher_good_threshold,
matcher_rating_margin,
Thresholds);
} /* GetAdaptThresholds */
| UNICHAR_ID * tesseract::Classify::GetAmbiguities | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| CLASS_ID | CorrectClass | ||
| ) |
This routine matches blob to the built-in templates to find out if there are any classes other than the correct class which are potential ambiguities.
| Blob | blob to get classification ambiguities for |
| denorm | normalization/denormalization parameters |
| CorrectClass | correct class for Blob |
Globals:
Definition at line 1893 of file adaptmatch.cpp.
{
ADAPT_RESULTS *Results = new ADAPT_RESULTS();
UNICHAR_ID *Ambiguities;
int i;
Results->Initialize();
CharNormClassifier(Blob, denorm, PreTrainedTemplates, Results);
RemoveBadMatches(Results);
qsort((void *)Results->match, Results->NumMatches,
sizeof(ScoredClass), CompareByRating);
/* copy the class id's into an string of ambiguities - don't copy if
the correct class is the only class id matched */
Ambiguities = (UNICHAR_ID *) Emalloc (sizeof (UNICHAR_ID) *
(Results->NumMatches + 1));
if (Results->NumMatches > 1 ||
(Results->NumMatches == 1 &&
Results->match[0].unichar_id != CorrectClass)) {
for (i = 0; i < Results->NumMatches; i++)
Ambiguities[i] = Results->match[i].unichar_id;
Ambiguities[i] = -1;
} else {
Ambiguities[0] = -1;
}
delete Results;
return Ambiguities;
} /* GetAmbiguities */
| int tesseract::Classify::GetBaselineFeatures | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| INT_TEMPLATES | Templates, | ||
| INT_FEATURE_ARRAY | IntFeatures, | ||
| uinT8 * | CharNormArray, | ||
| inT32 * | BlobLength | ||
| ) |
This routine calls the integer (Hardware) feature extractor if it has not been called before for this blob. The results from the feature extractor are placed into globals so that they can be used in other routines without re-extracting the features. It then copies the baseline features into the IntFeatures array provided by the caller.
| Blob | blob to extract features from |
| denorm | normalization/denormalization parameters |
| Templates | used to compute char norm adjustments |
| IntFeatures | array to fill with integer features |
| CharNormArray | array to fill with dummy char norm adjustments |
| BlobLength | length of blob in baseline-normalized units |
Globals:
Definition at line 1952 of file adaptmatch.cpp.
{
register INT_FEATURE Src, Dest, End;
if (!FeaturesHaveBeenExtracted) {
FeaturesOK = ExtractIntFeat(Blob, denorm, BaselineFeatures,
CharNormFeatures, &FXInfo, NULL);
FeaturesHaveBeenExtracted = TRUE;
}
if (!FeaturesOK) {
*BlobLength = FXInfo.NumBL;
return 0;
}
for (Src = BaselineFeatures, End = Src + FXInfo.NumBL, Dest = IntFeatures;
Src < End;
*Dest++ = *Src++);
ClearCharNormArray(CharNormArray);
*BlobLength = FXInfo.NumBL;
return FXInfo.NumBL;
} /* GetBaselineFeatures */
| int tesseract::Classify::GetCharNormFeatures | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| INT_TEMPLATES | Templates, | ||
| INT_FEATURE_ARRAY | IntFeatures, | ||
| uinT8 * | PrunerNormArray, | ||
| uinT8 * | CharNormArray, | ||
| inT32 * | BlobLength, | ||
| inT32 * | FeatureOutlineArray | ||
| ) |
This routine calls the integer (Hardware) feature extractor if it has not been called before for this blob.
The results from the feature extractor are placed into globals so that they can be used in other routines without re-extracting the features.
It then copies the char norm features into the IntFeatures array provided by the caller.
| Blob | blob to extract features from |
| denorm | normalization/denormalization parameters |
| Templates | used to compute char norm adjustments |
| IntFeatures | array to fill with integer features |
| PrunerNormArray | Array of factors from blob normalization process |
| CharNormArray | array to fill with dummy char norm adjustments |
| BlobLength | length of blob in baseline-normalized units |
| FeatureOutlineArray | Globals:
|
Definition at line 2040 of file adaptmatch.cpp.
{
register INT_FEATURE Src, Dest, End;
FEATURE NormFeature;
FLOAT32 Baseline, Scale;
inT32 FeatureOutlineIndex[MAX_NUM_INT_FEATURES];
if (!FeaturesHaveBeenExtracted) {
FeaturesOK = ExtractIntFeat(Blob, denorm, BaselineFeatures,
CharNormFeatures, &FXInfo,
FeatureOutlineIndex);
FeaturesHaveBeenExtracted = TRUE;
}
if (!FeaturesOK) {
*BlobLength = FXInfo.NumBL;
return (0);
}
for (Src = CharNormFeatures, End = Src + FXInfo.NumCN, Dest = IntFeatures;
Src < End;
*Dest++ = *Src++);
for (int i = 0; FeatureOutlineArray && i < FXInfo.NumCN; ++i) {
FeatureOutlineArray[i] = FeatureOutlineIndex[i];
}
NormFeature = NewFeature(&CharNormDesc);
Baseline = BASELINE_OFFSET;
Scale = MF_SCALE_FACTOR;
NormFeature->Params[CharNormY] = (FXInfo.Ymean - Baseline) * Scale;
NormFeature->Params[CharNormLength] =
FXInfo.Length * Scale / LENGTH_COMPRESSION;
NormFeature->Params[CharNormRx] = FXInfo.Rx * Scale;
NormFeature->Params[CharNormRy] = FXInfo.Ry * Scale;
ComputeCharNormArrays(NormFeature, Templates, CharNormArray, PrunerNormArray);
*BlobLength = FXInfo.NumBL;
return (FXInfo.NumCN);
} /* GetCharNormFeatures */
| CLASS_ID tesseract::Classify::GetClassToDebug | ( | const char * | Prompt, |
| bool * | adaptive_on, | ||
| bool * | pretrained_on, | ||
| int * | shape_id | ||
| ) |
Definition at line 1432 of file intproto.cpp.
{
/*
** Parameters:
** Prompt prompt to print while waiting for input from window
** Globals: none
** Operation: This routine prompts the user with Prompt and waits
** for the user to enter something in the debug window.
** Return: Character entered in the debug window.
** Exceptions: none
** History: Thu Mar 21 16:55:13 1991, DSJ, Created.
*/
tprintf("%s\n", Prompt);
SVEvent* ev;
SVEventType ev_type;
int unichar_id = INVALID_UNICHAR_ID;
// Wait until a click or popup event.
do {
ev = IntMatchWindow->AwaitEvent(SVET_ANY);
ev_type = ev->type;
if (ev_type == SVET_POPUP) {
if (ev->command_id == IDA_SHAPE_INDEX) {
if (shape_table_ != NULL) {
*shape_id = atoi(ev->parameter);
*adaptive_on = false;
*pretrained_on = true;
if (*shape_id >= 0 && *shape_id < shape_table_->NumShapes()) {
int font_id;
shape_table_->GetFirstUnicharAndFont(*shape_id, &unichar_id,
&font_id);
tprintf("Shape %d, first unichar=%d, font=%d\n",
*shape_id, unichar_id, font_id);
return unichar_id;
}
tprintf("Shape index '%s' not found in shape table\n", ev->parameter);
} else {
tprintf("No shape table loaded!\n");
}
} else {
if (unicharset.contains_unichar(ev->parameter)) {
unichar_id = unicharset.unichar_to_id(ev->parameter);
if (ev->command_id == IDA_ADAPTIVE) {
*adaptive_on = true;
*pretrained_on = false;
*shape_id = -1;
} else if (ev->command_id == IDA_STATIC) {
*adaptive_on = false;
*pretrained_on = true;
} else {
*adaptive_on = true;
*pretrained_on = true;
}
if (ev->command_id == IDA_ADAPTIVE || shape_table_ == NULL) {
*shape_id = -1;
return unichar_id;
}
for (int s = 0; s < shape_table_->NumShapes(); ++s) {
if (shape_table_->GetShape(s).ContainsUnichar(unichar_id)) {
tprintf("%s\n", shape_table_->DebugStr(s).string());
}
}
} else {
tprintf("Char class '%s' not found in unicharset",
ev->parameter);
}
}
}
delete ev;
} while (ev_type != SVET_CLICK);
return 0;
} /* GetClassToDebug */
| Dict& tesseract::Classify::getDict | ( | ) | [inline] |
Definition at line 62 of file classify.h.
{
return dict_;
}
| int tesseract::Classify::GetFontinfoId | ( | ADAPT_CLASS | Class, |
| uinT8 | ConfigId | ||
| ) |
Definition at line 190 of file adaptive.cpp.
{
return (ConfigIsPermanent(Class, ConfigId) ?
PermConfigFor(Class, ConfigId)->FontinfoId :
TempConfigFor(Class, ConfigId)->FontinfoId);
}
| void tesseract::Classify::InitAdaptedClass | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| CLASS_ID | ClassId, | ||
| int | FontinfoId, | ||
| ADAPT_CLASS | Class, | ||
| ADAPT_TEMPLATES | Templates | ||
| ) |
This routine creates a new adapted class and uses Blob as the model for the first config in that class.
| Blob | blob to model new class after |
| denorm | normalization/denormalization parameters |
| ClassId | id of the class to be initialized |
| FontinfoId | font information inferred from pre-trained templates |
| Class | adapted class to be initialized |
| Templates | adapted templates to add new class to |
Globals:
Definition at line 760 of file adaptmatch.cpp.
{
FEATURE_SET Features;
int Fid, Pid;
FEATURE Feature;
int NumFeatures;
TEMP_PROTO TempProto;
PROTO Proto;
INT_CLASS IClass;
TEMP_CONFIG Config;
classify_norm_method.set_value(baseline);
Features = ExtractOutlineFeatures(Blob);
NumFeatures = Features->NumFeatures;
if (NumFeatures > UNLIKELY_NUM_FEAT || NumFeatures <= 0) {
FreeFeatureSet(Features);
return;
}
Config = NewTempConfig(NumFeatures - 1, FontinfoId);
TempConfigFor(Class, 0) = Config;
/* this is a kludge to construct cutoffs for adapted templates */
if (Templates == AdaptedTemplates)
BaselineCutoffs[ClassId] = CharNormCutoffs[ClassId];
IClass = ClassForClassId (Templates->Templates, ClassId);
for (Fid = 0; Fid < Features->NumFeatures; Fid++) {
Pid = AddIntProto (IClass);
assert (Pid != NO_PROTO);
Feature = Features->Features[Fid];
TempProto = NewTempProto ();
Proto = &(TempProto->Proto);
/* compute proto params - NOTE that Y_DIM_OFFSET must be used because
ConvertProto assumes that the Y dimension varies from -0.5 to 0.5
instead of the -0.25 to 0.75 used in baseline normalization */
Proto->Angle = Feature->Params[OutlineFeatDir];
Proto->X = Feature->Params[OutlineFeatX];
Proto->Y = Feature->Params[OutlineFeatY] - Y_DIM_OFFSET;
Proto->Length = Feature->Params[OutlineFeatLength];
FillABC(Proto);
TempProto->ProtoId = Pid;
SET_BIT (Config->Protos, Pid);
ConvertProto(Proto, Pid, IClass);
AddProtoToProtoPruner(Proto, Pid, IClass,
classify_learning_debug_level >= 2);
Class->TempProtos = push (Class->TempProtos, TempProto);
}
FreeFeatureSet(Features);
AddIntConfig(IClass);
ConvertConfig (AllProtosOn, 0, IClass);
if (classify_learning_debug_level >= 1) {
cprintf ("Added new class '%s' with class id %d and %d protos.\n",
unicharset.id_to_unichar(ClassId), ClassId, NumFeatures);
if (classify_learning_debug_level > 1)
DisplayAdaptedChar(Blob, denorm, IClass);
}
if (IsEmptyAdaptedClass(Class))
(Templates->NumNonEmptyClasses)++;
} /* InitAdaptedClass */
| void tesseract::Classify::InitAdaptiveClassifier | ( | bool | load_pre_trained_templates | ) |
This routine reads in the training information needed by the adaptive classifier and saves it into global variables. Parameters: load_pre_trained_templates Indicates whether the pre-trained templates (inttemp, normproto and pffmtable components) should be lodaded. Should only be set to true if the necesary classifier components are present in the [lang].traineddata file. Globals: BuiltInTemplatesFile file to get built-in temps from BuiltInCutoffsFile file to get avg. feat per class from classify_use_pre_adapted_templates enables use of pre-adapted templates
Definition at line 547 of file adaptmatch.cpp.
{
if (!classify_enable_adaptive_matcher)
return;
if (AllProtosOn != NULL)
EndAdaptiveClassifier(); // Don't leak with multiple inits.
// If there is no language_data_path_prefix, the classifier will be
// adaptive only.
if (language_data_path_prefix.length() > 0 &&
load_pre_trained_templates) {
ASSERT_HOST(tessdata_manager.SeekToStart(TESSDATA_INTTEMP));
PreTrainedTemplates =
ReadIntTemplates(tessdata_manager.GetDataFilePtr());
if (tessdata_manager.DebugLevel() > 0) tprintf("Loaded inttemp\n");
if (tessdata_manager.SeekToStart(TESSDATA_SHAPE_TABLE)) {
shape_table_ = new ShapeTable(unicharset);
if (!shape_table_->DeSerialize(tessdata_manager.swap(),
tessdata_manager.GetDataFilePtr())) {
tprintf("Error loading shape table!\n");
delete shape_table_;
shape_table_ = NULL;
} else if (tessdata_manager.DebugLevel() > 0) {
tprintf("Successfully loaded shape table!\n");
}
}
ASSERT_HOST(tessdata_manager.SeekToStart(TESSDATA_PFFMTABLE));
ReadNewCutoffs(tessdata_manager.GetDataFilePtr(),
tessdata_manager.swap(),
tessdata_manager.GetEndOffset(TESSDATA_PFFMTABLE),
CharNormCutoffs);
if (tessdata_manager.DebugLevel() > 0) tprintf("Loaded pffmtable\n");
ASSERT_HOST(tessdata_manager.SeekToStart(TESSDATA_NORMPROTO));
NormProtos =
ReadNormProtos(tessdata_manager.GetDataFilePtr(),
tessdata_manager.GetEndOffset(TESSDATA_NORMPROTO));
if (tessdata_manager.DebugLevel() > 0) tprintf("Loaded normproto\n");
}
im_.Init(&classify_debug_level, classify_integer_matcher_multiplier);
InitIntegerFX();
AllProtosOn = NewBitVector(MAX_NUM_PROTOS);
PrunedProtos = NewBitVector(MAX_NUM_PROTOS);
AllConfigsOn = NewBitVector(MAX_NUM_CONFIGS);
AllProtosOff = NewBitVector(MAX_NUM_PROTOS);
AllConfigsOff = NewBitVector(MAX_NUM_CONFIGS);
TempProtoMask = NewBitVector(MAX_NUM_PROTOS);
set_all_bits(AllProtosOn, WordsInVectorOfSize(MAX_NUM_PROTOS));
set_all_bits(PrunedProtos, WordsInVectorOfSize(MAX_NUM_PROTOS));
set_all_bits(AllConfigsOn, WordsInVectorOfSize(MAX_NUM_CONFIGS));
zero_all_bits(AllProtosOff, WordsInVectorOfSize(MAX_NUM_PROTOS));
zero_all_bits(AllConfigsOff, WordsInVectorOfSize(MAX_NUM_CONFIGS));
for (int i = 0; i < MAX_NUM_CLASSES; i++) {
BaselineCutoffs[i] = 0;
}
if (classify_use_pre_adapted_templates) {
FILE *File;
STRING Filename;
Filename = imagefile;
Filename += ADAPT_TEMPLATE_SUFFIX;
File = fopen(Filename.string(), "rb");
if (File == NULL) {
AdaptedTemplates = NewAdaptedTemplates(true);
} else {
#ifndef SECURE_NAMES
cprintf("\nReading pre-adapted templates from %s ...\n",
Filename.string());
fflush(stdout);
#endif
AdaptedTemplates = ReadAdaptedTemplates(File);
cprintf("\n");
fclose(File);
PrintAdaptedTemplates(stdout, AdaptedTemplates);
for (int i = 0; i < AdaptedTemplates->Templates->NumClasses; i++) {
BaselineCutoffs[i] = CharNormCutoffs[i];
}
}
} else {
if (AdaptedTemplates != NULL)
free_adapted_templates(AdaptedTemplates);
AdaptedTemplates = NewAdaptedTemplates(true);
}
} /* InitAdaptiveClassifier */
| void tesseract::Classify::LearnPieces | ( | const char * | filename, |
| int | start, | ||
| int | length, | ||
| float | threshold, | ||
| CharSegmentationType | segmentation, | ||
| const char * | correct_text, | ||
| WERD_RES * | word | ||
| ) |
Definition at line 396 of file adaptmatch.cpp.
{
// TODO(daria) Remove/modify this if/when we want
// to train and/or adapt to n-grams.
if (segmentation != CST_WHOLE &&
(segmentation != CST_FRAGMENT || disable_character_fragments))
return;
if (length > 1) {
join_pieces(word->chopped_word->blobs, word->seam_array,
start, start + length - 1);
}
TBLOB* blob = word->chopped_word->blobs;
for (int i = 0; i < start; ++i)
blob = blob->next;
// Rotate the blob if needed for classification.
const DENORM* denorm = &word->denorm;
TBLOB* rotated_blob = blob->ClassifyNormalizeIfNeeded(&denorm);
if (rotated_blob == NULL)
rotated_blob = blob;
#ifndef GRAPHICS_DISABLED
// Draw debug windows showing the blob that is being learned if needed.
if (strcmp(classify_learn_debug_str.string(), correct_text) == 0) {
RefreshDebugWindow(&learn_debug_win_, "LearnPieces", 600,
word->chopped_word->bounding_box());
rotated_blob->plot(learn_debug_win_, ScrollView::GREEN, ScrollView::BROWN);
learn_debug_win_->Update();
window_wait(learn_debug_win_);
}
if (classify_debug_character_fragments && segmentation == CST_FRAGMENT) {
ASSERT_HOST(learn_fragments_debug_win_ != NULL); // set up in LearnWord
blob->plot(learn_fragments_debug_win_,
ScrollView::BLUE, ScrollView::BROWN);
learn_fragments_debug_win_->Update();
}
#endif // GRAPHICS_DISABLED
if (filename != NULL) {
classify_norm_method.set_value(character); // force char norm spc 30/11/93
tess_bn_matching.set_value(false); // turn it off
tess_cn_matching.set_value(false);
LearnBlob(feature_defs_, filename, rotated_blob, *denorm,
correct_text);
} else if (unicharset.contains_unichar(correct_text)) {
UNICHAR_ID class_id = unicharset.unichar_to_id(correct_text);
int font_id = word->fontinfo != NULL
? fontinfo_table_.get_id(*word->fontinfo)
: 0;
if (classify_learning_debug_level >= 1)
tprintf("Adapting to char = %s, thr= %g font_id= %d\n",
unicharset.id_to_unichar(class_id), threshold, font_id);
// If filename is not NULL we are doing recognition
// (as opposed to training), so we must have already set word fonts.
AdaptToChar(rotated_blob, *denorm, class_id, font_id, threshold);
} else if (classify_debug_level >= 1) {
tprintf("Can't adapt to %s not in unicharset\n", correct_text);
}
if (rotated_blob != blob) {
delete rotated_blob;
delete denorm;
}
break_pieces(blob, word->seam_array, start, start + length - 1);
} // LearnPieces.
| void tesseract::Classify::LearnWord | ( | const char * | filename, |
| const char * | rejmap, | ||
| WERD_RES * | word | ||
| ) |
Definition at line 256 of file adaptmatch.cpp.
{
int word_len = word->correct_text.size();
if (word_len == 0) return;
float* thresholds = NULL;
if (filename == NULL) {
// Adaption mode.
if (!EnableLearning || word->best_choice == NULL ||
// If word->best_choice is not recorded at the top of accumulator's
// best choices (which could happen for choices that are
// altered with ReplaceAmbig()) we skip the adaption.
!getDict().CurrentBestChoiceIs(*(word->best_choice)))
return; // Can't or won't adapt.
NumWordsAdaptedTo++;
if (classify_learning_debug_level >= 1)
tprintf("\n\nAdapting to word = %s\n",
word->best_choice->debug_string().string());
thresholds = new float[word_len];
GetAdaptThresholds(word->rebuild_word, word->denorm, *word->best_choice,
*word->raw_choice, thresholds);
}
int start_blob = 0;
char prev_map_char = '0';
#ifndef GRAPHICS_DISABLED
if (classify_debug_character_fragments) {
if (learn_fragmented_word_debug_win_ != NULL) {
window_wait(learn_fragmented_word_debug_win_);
}
RefreshDebugWindow(&learn_fragments_debug_win_, "LearnPieces", 400,
word->chopped_word->bounding_box());
RefreshDebugWindow(&learn_fragmented_word_debug_win_, "LearnWord", 200,
word->chopped_word->bounding_box());
word->chopped_word->plot(learn_fragmented_word_debug_win_);
ScrollView::Update();
}
#endif // GRAPHICS_DISABLED
for (int ch = 0; ch < word_len; ++ch) {
if (classify_debug_character_fragments) {
tprintf("\nLearning %s\n", word->correct_text[ch].string());
}
char rej_map_char = rejmap != NULL ? *rejmap++ : '1';
if (word->correct_text[ch].length() > 0 && rej_map_char == '1') {
float threshold = thresholds != NULL ? thresholds[ch] : 0.0f;
LearnPieces(filename, start_blob, word->best_state[ch],
threshold, CST_WHOLE, word->correct_text[ch].string(), word);
if (word->best_state[ch] > 1 && !disable_character_fragments) {
// Check that the character breaks into meaningful fragments
// that each match a whole character with at least
// classify_character_fragments_garbage_certainty_threshold
bool garbage = false;
TBLOB* frag_blob = word->chopped_word->blobs;
for (int i = 0; i < start_blob; ++i) frag_blob = frag_blob->next;
int frag;
for (frag = 0; frag < word->best_state[ch]; ++frag) {
if (classify_character_fragments_garbage_certainty_threshold < 0) {
garbage |= LooksLikeGarbage(word->denorm, frag_blob);
}
frag_blob = frag_blob->next;
}
// Learn the fragments.
if (!garbage) {
bool pieces_all_natural = word->PiecesAllNatural(start_blob,
word->best_state[ch]);
if (pieces_all_natural || !prioritize_division) {
for (frag = 0; frag < word->best_state[ch]; ++frag) {
GenericVector<STRING> tokens;
word->correct_text[ch].split(' ', &tokens);
tokens[0] = CHAR_FRAGMENT::to_string(
tokens[0].string(), frag, word->best_state[ch],
pieces_all_natural);
STRING full_string;
for (int i = 0; i < tokens.size(); i++) {
full_string += tokens[i];
if (i != tokens.size() - 1)
full_string += ' ';
}
LearnPieces(filename, start_blob + frag, 1,
threshold, CST_FRAGMENT, full_string.string(), word);
}
}
}
}
// TODO(rays): re-enable this part of the code when we switch to the
// new classifier that needs to see examples of garbage.
/*
char next_map_char = ch + 1 < word_len
? (rejmap != NULL ? *rejmap : '1')
: '0';
if (word->best_state[ch] > 1) {
// If the next blob is good, make junk with the rightmost fragment.
if (ch + 1 < word_len && word->correct_text[ch + 1].length() > 0 &&
next_map_char == '1') {
LearnPieces(filename, start_blob + word->best_state[ch] - 1,
word->best_state[ch + 1] + 1,
threshold, CST_IMPROPER, INVALID_UNICHAR, word);
}
// If the previous blob is good, make junk with the leftmost fragment.
if (ch > 0 && word->correct_text[ch - 1].length() > 0 &&
prev_map_char == '1') {
LearnPieces(filename, start_blob - word->best_state[ch - 1],
word->best_state[ch - 1] + 1,
threshold, CST_IMPROPER, INVALID_UNICHAR, word);
}
}
// If the next blob is good, make a join with it.
if (ch + 1 < word_len && word->correct_text[ch + 1].length() > 0 &&
next_map_char == '1') {
STRING joined_text = word->correct_text[ch];
joined_text += word->correct_text[ch + 1];
LearnPieces(filename, start_blob,
word->best_state[ch] + word->best_state[ch + 1],
threshold, CST_NGRAM, joined_text.string(), word);
}
*/
}
start_blob += word->best_state[ch];
prev_map_char = rej_map_char;
}
delete [] thresholds;
} // LearnWord.
Definition at line 1986 of file adaptmatch.cpp.
{
BLOB_CHOICE_LIST *ratings = new BLOB_CHOICE_LIST();
AdaptiveClassifier(blob, denorm, ratings, NULL);
BLOB_CHOICE_IT ratings_it(ratings);
const UNICHARSET &unicharset = getDict().getUnicharset();
if (classify_debug_character_fragments) {
print_ratings_list("======================\nLooksLikeGarbage() got ",
ratings, unicharset);
}
for (ratings_it.mark_cycle_pt(); !ratings_it.cycled_list();
ratings_it.forward()) {
if (unicharset.get_fragment(ratings_it.data()->unichar_id()) != NULL) {
continue;
}
delete ratings;
return (ratings_it.data()->certainty() <
classify_character_fragments_garbage_certainty_threshold);
}
delete ratings;
return true; // no whole characters in ratings
}
| int tesseract::Classify::MakeNewTemporaryConfig | ( | ADAPT_TEMPLATES | Templates, |
| CLASS_ID | ClassId, | ||
| int | FontinfoId, | ||
| int | NumFeatures, | ||
| INT_FEATURE_ARRAY | Features, | ||
| FEATURE_SET | FloatFeatures | ||
| ) |
| Templates | adapted templates to add new config to |
| ClassId | class id to associate with new config |
| FontinfoId | font information inferred from pre-trained templates |
| NumFeatures | number of features in IntFeatures |
| Features | features describing model for new config |
| FloatFeatures | floating-pt representation of features |
Definition at line 2131 of file adaptmatch.cpp.
{
INT_CLASS IClass;
ADAPT_CLASS Class;
PROTO_ID OldProtos[MAX_NUM_PROTOS];
FEATURE_ID BadFeatures[MAX_NUM_INT_FEATURES];
int NumOldProtos;
int NumBadFeatures;
int MaxProtoId, OldMaxProtoId;
int BlobLength = 0;
int MaskSize;
int ConfigId;
TEMP_CONFIG Config;
int i;
int debug_level = NO_DEBUG;
if (classify_learning_debug_level >= 3)
debug_level =
PRINT_MATCH_SUMMARY | PRINT_FEATURE_MATCHES | PRINT_PROTO_MATCHES;
IClass = ClassForClassId(Templates->Templates, ClassId);
Class = Templates->Class[ClassId];
if (IClass->NumConfigs >= MAX_NUM_CONFIGS) {
++NumAdaptationsFailed;
if (classify_learning_debug_level >= 1)
cprintf("Cannot make new temporary config: maximum number exceeded.\n");
return -1;
}
OldMaxProtoId = IClass->NumProtos - 1;
NumOldProtos = im_.FindGoodProtos(IClass, AllProtosOn, AllConfigsOff,
BlobLength, NumFeatures, Features,
OldProtos, classify_adapt_proto_threshold,
debug_level);
MaskSize = WordsInVectorOfSize(MAX_NUM_PROTOS);
zero_all_bits(TempProtoMask, MaskSize);
for (i = 0; i < NumOldProtos; i++)
SET_BIT(TempProtoMask, OldProtos[i]);
NumBadFeatures = im_.FindBadFeatures(IClass, TempProtoMask, AllConfigsOn,
BlobLength, NumFeatures, Features,
BadFeatures,
classify_adapt_feature_threshold,
debug_level);
MaxProtoId = MakeNewTempProtos(FloatFeatures, NumBadFeatures, BadFeatures,
IClass, Class, TempProtoMask);
if (MaxProtoId == NO_PROTO) {
++NumAdaptationsFailed;
if (classify_learning_debug_level >= 1)
cprintf("Cannot make new temp protos: maximum number exceeded.\n");
return -1;
}
ConfigId = AddIntConfig(IClass);
ConvertConfig(TempProtoMask, ConfigId, IClass);
Config = NewTempConfig(MaxProtoId, FontinfoId);
TempConfigFor(Class, ConfigId) = Config;
copy_all_bits(TempProtoMask, Config->Protos, Config->ProtoVectorSize);
if (classify_learning_debug_level >= 1)
cprintf("Making new temp config %d fontinfo id %d"
" using %d old and %d new protos.\n",
ConfigId, Config->FontinfoId,
NumOldProtos, MaxProtoId - OldMaxProtoId);
return ConfigId;
} /* MakeNewTemporaryConfig */
| PROTO_ID tesseract::Classify::MakeNewTempProtos | ( | FEATURE_SET | Features, |
| int | NumBadFeat, | ||
| FEATURE_ID | BadFeat[], | ||
| INT_CLASS | IClass, | ||
| ADAPT_CLASS | Class, | ||
| BIT_VECTOR | TempProtoMask | ||
| ) |
This routine finds sets of sequential bad features that all have the same angle and converts each set into a new temporary proto. The temp proto is added to the proto pruner for IClass, pushed onto the list of temp protos in Class, and added to TempProtoMask.
| Features | floating-pt features describing new character |
| NumBadFeat | number of bad features to turn into protos |
| BadFeat | feature id's of bad features |
| IClass | integer class templates to add new protos to |
| Class | adapted class templates to add new protos to |
| TempProtoMask | proto mask to add new protos to |
Globals: none
Definition at line 2228 of file adaptmatch.cpp.
{
FEATURE_ID *ProtoStart;
FEATURE_ID *ProtoEnd;
FEATURE_ID *LastBad;
TEMP_PROTO TempProto;
PROTO Proto;
FEATURE F1, F2;
FLOAT32 X1, X2, Y1, Y2;
FLOAT32 A1, A2, AngleDelta;
FLOAT32 SegmentLength;
PROTO_ID Pid;
for (ProtoStart = BadFeat, LastBad = ProtoStart + NumBadFeat;
ProtoStart < LastBad; ProtoStart = ProtoEnd) {
F1 = Features->Features[*ProtoStart];
X1 = F1->Params[PicoFeatX];
Y1 = F1->Params[PicoFeatY];
A1 = F1->Params[PicoFeatDir];
for (ProtoEnd = ProtoStart + 1,
SegmentLength = GetPicoFeatureLength();
ProtoEnd < LastBad;
ProtoEnd++, SegmentLength += GetPicoFeatureLength()) {
F2 = Features->Features[*ProtoEnd];
X2 = F2->Params[PicoFeatX];
Y2 = F2->Params[PicoFeatY];
A2 = F2->Params[PicoFeatDir];
AngleDelta = fabs(A1 - A2);
if (AngleDelta > 0.5)
AngleDelta = 1.0 - AngleDelta;
if (AngleDelta > matcher_clustering_max_angle_delta ||
fabs(X1 - X2) > SegmentLength ||
fabs(Y1 - Y2) > SegmentLength)
break;
}
F2 = Features->Features[*(ProtoEnd - 1)];
X2 = F2->Params[PicoFeatX];
Y2 = F2->Params[PicoFeatY];
A2 = F2->Params[PicoFeatDir];
Pid = AddIntProto(IClass);
if (Pid == NO_PROTO)
return (NO_PROTO);
TempProto = NewTempProto();
Proto = &(TempProto->Proto);
/* compute proto params - NOTE that Y_DIM_OFFSET must be used because
ConvertProto assumes that the Y dimension varies from -0.5 to 0.5
instead of the -0.25 to 0.75 used in baseline normalization */
Proto->Length = SegmentLength;
Proto->Angle = A1;
Proto->X = (X1 + X2) / 2.0;
Proto->Y = (Y1 + Y2) / 2.0 - Y_DIM_OFFSET;
FillABC(Proto);
TempProto->ProtoId = Pid;
SET_BIT(TempProtoMask, Pid);
ConvertProto(Proto, Pid, IClass);
AddProtoToProtoPruner(Proto, Pid, IClass,
classify_learning_debug_level >= 2);
Class->TempProtos = push(Class->TempProtos, TempProto);
}
return IClass->NumProtos - 1;
} /* MakeNewTempProtos */
| void tesseract::Classify::MakePermanent | ( | ADAPT_TEMPLATES | Templates, |
| CLASS_ID | ClassId, | ||
| int | ConfigId, | ||
| const DENORM & | denorm, | ||
| TBLOB * | Blob | ||
| ) |
| Templates | current set of adaptive templates |
| ClassId | class containing config to be made permanent |
| ConfigId | config to be made permanent |
| denorm | normalization/denormalization parameters |
| Blob | current blob being adapted to |
Globals: none
Definition at line 2318 of file adaptmatch.cpp.
{
UNICHAR_ID *Ambigs;
TEMP_CONFIG Config;
ADAPT_CLASS Class;
PROTO_KEY ProtoKey;
Class = Templates->Class[ClassId];
Config = TempConfigFor(Class, ConfigId);
MakeConfigPermanent(Class, ConfigId);
if (Class->NumPermConfigs == 0)
Templates->NumPermClasses++;
Class->NumPermConfigs++;
// Initialize permanent config.
Ambigs = GetAmbiguities(Blob, denorm, ClassId);
PERM_CONFIG Perm = (PERM_CONFIG) alloc_struct(sizeof(PERM_CONFIG_STRUCT),
"PERM_CONFIG_STRUCT");
Perm->Ambigs = Ambigs;
Perm->FontinfoId = Config->FontinfoId;
// Free memory associated with temporary config (since ADAPTED_CONFIG
// is a union we need to clean up before we record permanent config).
ProtoKey.Templates = Templates;
ProtoKey.ClassId = ClassId;
ProtoKey.ConfigId = ConfigId;
Class->TempProtos = delete_d(Class->TempProtos, &ProtoKey, MakeTempProtoPerm);
FreeTempConfig(Config);
// Record permanent config.
PermConfigFor(Class, ConfigId) = Perm;
if (classify_learning_debug_level >= 1) {
tprintf("Making config %d for %s (ClassId %d) permanent:"
" fontinfo id %d, ambiguities '",
ConfigId, getDict().getUnicharset().debug_str(ClassId).string(),
ClassId, PermConfigFor(Class, ConfigId)->FontinfoId);
for (UNICHAR_ID *AmbigsPointer = Ambigs;
*AmbigsPointer >= 0; ++AmbigsPointer)
tprintf("%s", unicharset.id_to_unichar(*AmbigsPointer));
tprintf("'.\n");
}
} /* MakePermanent */
| void tesseract::Classify::MasterMatcher | ( | INT_TEMPLATES | templates, |
| inT16 | num_features, | ||
| const INT_FEATURE_STRUCT * | features, | ||
| const uinT8 * | norm_factors, | ||
| ADAPT_CLASS * | classes, | ||
| int | debug, | ||
| int | num_classes, | ||
| const TBOX & | blob_box, | ||
| CLASS_PRUNER_RESULTS | results, | ||
| ADAPT_RESULTS * | final_results | ||
| ) |
Factored-out calls to IntegerMatcher based on class pruner results. Returns integer matcher results inside CLASS_PRUNER_RESULTS structure.
Definition at line 1252 of file adaptmatch.cpp.
{
int top = blob_box.top();
int bottom = blob_box.bottom();
for (int c = 0; c < num_classes; c++) {
CLASS_ID class_id = results[c].Class;
INT_RESULT_STRUCT& int_result = results[c].IMResult;
BIT_VECTOR protos = classes != NULL ? classes[class_id]->PermProtos
: AllProtosOn;
BIT_VECTOR configs = classes != NULL ? classes[class_id]->PermConfigs
: AllConfigsOn;
im_.Match(ClassForClassId(templates, class_id),
protos, configs,
num_features, features,
&int_result, classify_adapt_feature_threshold, debug,
matcher_debug_separate_windows);
bool debug = matcher_debug_level >= 2 || classify_debug_level > 1;
ExpandShapesAndApplyCorrections(classes, debug, class_id, bottom, top,
results[c].Rating,
final_results->BlobLength, norm_factors,
int_result, final_results);
}
}
| ADAPT_TEMPLATES tesseract::Classify::NewAdaptedTemplates | ( | bool | InitFromUnicharset | ) |
Allocates memory for adapted tempates. each char in unicharset to the newly created templates
| InitFromUnicharset | if true, add an empty class for |
Definition at line 167 of file adaptive.cpp.
{
ADAPT_TEMPLATES Templates;
int i;
Templates = (ADAPT_TEMPLATES) Emalloc (sizeof (ADAPT_TEMPLATES_STRUCT));
Templates->Templates = NewIntTemplates ();
Templates->NumPermClasses = 0;
Templates->NumNonEmptyClasses = 0;
/* Insert an empty class for each unichar id in unicharset */
for (i = 0; i < MAX_NUM_CLASSES; i++) {
Templates->Class[i] = NULL;
if (InitFromUnicharset && i < unicharset.size()) {
AddAdaptedClass(Templates, NewAdaptedClass(), i);
}
}
return (Templates);
} /* NewAdaptedTemplates */
Definition at line 346 of file mfoutline.cpp.
{
/*
** Parameters:
** Outlines list of outlines to be normalized
** XScale x-direction scale factor used by routine
** YScale y-direction scale factor used by routine
** Globals:
** classify_norm_method method being used for normalization
** classify_char_norm_range map radius of gyration to this value
** Operation: This routine normalizes every outline in Outlines
** according to the currently selected normalization method.
** It also returns the scale factors that it used to do this
** scaling. The scale factors returned represent the x and
** y sizes in the normalized coordinate system that correspond
** to 1 pixel in the original coordinate system.
** Return: none (Outlines are changed and XScale and YScale are updated)
** Exceptions: none
** History: Fri Dec 14 08:14:55 1990, DSJ, Created.
*/
MFOUTLINE Outline;
OUTLINE_STATS OutlineStats;
FLOAT32 BaselineScale;
switch (classify_norm_method) {
case character:
ComputeOutlineStats(Outlines, &OutlineStats);
/* limit scale factor to avoid overscaling small blobs (.,`'),
thin blobs (l1ift), and merged blobs */
*XScale = *YScale = BaselineScale = MF_SCALE_FACTOR;
*XScale *= OutlineStats.Ry;
*YScale *= OutlineStats.Rx;
if (*XScale < classify_min_norm_scale_x)
*XScale = classify_min_norm_scale_x;
if (*YScale < classify_min_norm_scale_y)
*YScale = classify_min_norm_scale_y;
if (*XScale > classify_max_norm_scale_x &&
*YScale <= classify_max_norm_scale_y)
*XScale = classify_max_norm_scale_x;
*XScale = classify_char_norm_range * BaselineScale / *XScale;
*YScale = classify_char_norm_range * BaselineScale / *YScale;
iterate(Outlines) {
Outline = (MFOUTLINE) first_node (Outlines);
CharNormalizeOutline (Outline,
OutlineStats.x, OutlineStats.y,
*XScale, *YScale);
}
break;
case baseline:
iterate(Outlines) {
Outline = (MFOUTLINE) first_node(Outlines);
NormalizeOutline(Outline, 0.0);
}
*XScale = *YScale = MF_SCALE_FACTOR;
break;
}
} /* NormalizeOutlines */
| void tesseract::Classify::PrintAdaptedTemplates | ( | FILE * | File, |
| ADAPT_TEMPLATES | Templates | ||
| ) |
This routine prints a summary of the adapted templates in Templates to File.
| File | open text file to print Templates to |
| Templates | adapted templates to print to File |
Definition at line 273 of file adaptive.cpp.
{
int i;
INT_CLASS IClass;
ADAPT_CLASS AClass;
#ifndef SECURE_NAMES
fprintf (File, "\n\nSUMMARY OF ADAPTED TEMPLATES:\n\n");
fprintf (File, "Num classes = %d; Num permanent classes = %d\n\n",
Templates->NumNonEmptyClasses, Templates->NumPermClasses);
fprintf (File, " Id NC NPC NP NPP\n");
fprintf (File, "------------------------\n");
for (i = 0; i < (Templates->Templates)->NumClasses; i++) {
IClass = Templates->Templates->Class[i];
AClass = Templates->Class[i];
if (!IsEmptyAdaptedClass (AClass)) {
fprintf (File, "%5d %s %3d %3d %3d %3d\n",
i, unicharset.id_to_unichar(i),
IClass->NumConfigs, AClass->NumPermConfigs,
IClass->NumProtos,
IClass->NumProtos - count (AClass->TempProtos));
}
}
#endif
fprintf (File, "\n");
} /* PrintAdaptedTemplates */
| void tesseract::Classify::PrintAdaptiveMatchResults | ( | FILE * | File, |
| ADAPT_RESULTS * | Results | ||
| ) |
This routine writes the matches in Results to File.
| File | open text file to write Results to |
| Results | match results to write to File |
Globals: none
Definition at line 2419 of file adaptmatch.cpp.
{
for (int i = 0; i < Results->NumMatches; ++i) {
tprintf("%s(%d), shape %d, %.2f ",
unicharset.debug_str(Results->match[i].unichar_id).string(),
Results->match[i].unichar_id, Results->match[i].shape_id,
Results->match[i].rating * 100.0);
}
tprintf("\n");
} /* PrintAdaptiveMatchResults */
| void tesseract::Classify::PrintAdaptiveStatistics | ( | FILE * | File | ) |
Print to File the statistics which have been gathered for the adaptive matcher.
| File | open text file to print adaptive statistics to |
Globals: none
Definition at line 661 of file adaptmatch.cpp.
{
#ifndef SECURE_NAMES
fprintf (File, "\nADAPTIVE MATCHER STATISTICS:\n");
fprintf (File, "\tNum blobs classified = %d\n", AdaptiveMatcherCalls);
fprintf (File, "\tNum classes output = %d (Avg = %4.2f)\n",
NumClassesOutput,
((AdaptiveMatcherCalls == 0) ? (0.0) :
((float) NumClassesOutput / AdaptiveMatcherCalls)));
fprintf (File, "\t\tBaseline Classifier: %4d calls (%4.2f classes/call)\n",
BaselineClassifierCalls,
((BaselineClassifierCalls == 0) ? (0.0) :
((float) NumBaselineClassesTried / BaselineClassifierCalls)));
fprintf (File, "\t\tCharNorm Classifier: %4d calls (%4.2f classes/call)\n",
CharNormClassifierCalls,
((CharNormClassifierCalls == 0) ? (0.0) :
((float) NumCharNormClassesTried / CharNormClassifierCalls)));
fprintf (File, "\t\tAmbig Classifier: %4d calls (%4.2f classes/call)\n",
AmbigClassifierCalls,
((AmbigClassifierCalls == 0) ? (0.0) :
((float) NumAmbigClassesTried / AmbigClassifierCalls)));
fprintf (File, "\nADAPTIVE LEARNER STATISTICS:\n");
fprintf (File, "\tNumber of words adapted to: %d\n", NumWordsAdaptedTo);
fprintf (File, "\tNumber of chars adapted to: %d\n", NumCharsAdaptedTo);
PrintAdaptedTemplates(File, AdaptedTemplates);
#endif
} /* PrintAdaptiveStatistics */
| int tesseract::Classify::PruneClasses | ( | const INT_TEMPLATES_STRUCT * | int_templates, |
| int | num_features, | ||
| const INT_FEATURE_STRUCT * | features, | ||
| const uinT8 * | normalization_factors, | ||
| const uinT16 * | expected_num_features, | ||
| CP_RESULT_STRUCT * | results | ||
| ) |
Definition at line 405 of file intmatcher.cpp.
{
/*
** Operation:
** Prunes the classes using a modified fast match table.
** Returns a sorted list of classes along with the number
** of pruned classes in that list.
** Return: Number of pruned classes.
** Exceptions: none
** History: Tue Feb 19 10:24:24 MST 1991, RWM, Created.
*/
ClassPruner pruner(int_templates->NumClasses);
// Compute initial match scores for all classes.
pruner.ComputeScores(int_templates, num_features, features);
// Adjust match scores for number of expected features.
pruner.AdjustForExpectedNumFeatures(expected_num_features,
classify_cp_cutoff_strength);
// Apply disabled classes in unicharset - only works without a shape_table.
if (shape_table_ == NULL)
pruner.DisableDisabledClasses(unicharset);
// If fragments are disabled, remove them, also only without a shape table.
if (disable_character_fragments && shape_table_ == NULL)
pruner.DisableFragments(unicharset);
// If we have good x-heights, apply the given normalization factors.
if (normalization_factors != NULL) {
pruner.NormalizeForXheight(classify_class_pruner_multiplier,
normalization_factors);
} else {
pruner.NoNormalization();
}
// Do the actual pruning and sort the short-list.
pruner.PruneAndSort(classify_class_pruner_threshold,
shape_table_ == NULL, unicharset);
if (classify_debug_level > 2) {
pruner.DebugMatch(*this, int_templates, features);
}
if (classify_debug_level > 1) {
pruner.SummarizeResult(*this, int_templates, expected_num_features,
classify_class_pruner_multiplier,
normalization_factors);
}
// Convert to the expected output format.
return pruner.SetupResults(results);
}
| ADAPT_TEMPLATES tesseract::Classify::ReadAdaptedTemplates | ( | FILE * | File | ) |
Read a set of adapted templates from File and return a ptr to the templates.
| File | open text file to read adapted templates from |
Definition at line 371 of file adaptive.cpp.
{
int i;
ADAPT_TEMPLATES Templates;
/* first read the high level adaptive template struct */
Templates = (ADAPT_TEMPLATES) Emalloc (sizeof (ADAPT_TEMPLATES_STRUCT));
fread ((char *) Templates, sizeof (ADAPT_TEMPLATES_STRUCT), 1, File);
/* then read in the basic integer templates */
Templates->Templates = ReadIntTemplates (File);
/* then read in the adaptive info for each class */
for (i = 0; i < (Templates->Templates)->NumClasses; i++) {
Templates->Class[i] = ReadAdaptedClass (File);
}
return (Templates);
} /* ReadAdaptedTemplates */
| void tesseract::Classify::ReadClassFile | ( | ) |
Definition at line 293 of file protos.cpp.
{
FILE *File;
char TextLine[CHARS_PER_LINE];
char unichar[CHARS_PER_LINE];
cprintf ("Reading training data from '%s' ...",
static_cast<STRING>(classify_training_file).string());
fflush(stdout);
File = open_file(static_cast<STRING>(classify_training_file).string(), "r");
while (fgets (TextLine, CHARS_PER_LINE, File) != NULL) {
sscanf(TextLine, "%s", unichar);
ReadClassFromFile (File, unicharset.unichar_to_id(unichar));
fgets(TextLine, CHARS_PER_LINE, File);
fgets(TextLine, CHARS_PER_LINE, File);
}
fclose(File);
new_line();
}
| INT_TEMPLATES tesseract::Classify::ReadIntTemplates | ( | FILE * | File | ) |
Definition at line 786 of file intproto.cpp.
{
/*
** Parameters:
** File open file to read templates from
** Globals: none
** Operation: This routine reads a set of integer templates from
** File. File must already be open and must be in the
** correct binary format.
** Return: Pointer to integer templates read from File.
** Exceptions: none
** History: Wed Feb 27 11:48:46 1991, DSJ, Created.
*/
int i, j, w, x, y, z;
BOOL8 swap;
int nread;
int unicharset_size;
int version_id = 0;
INT_TEMPLATES Templates;
CLASS_PRUNER_STRUCT* Pruner;
INT_CLASS Class;
uinT8 *Lengths;
PROTO_SET ProtoSet;
/* variables for conversion from older inttemp formats */
int b, bit_number, last_cp_bit_number, new_b, new_i, new_w;
CLASS_ID class_id, max_class_id;
inT16 *IndexFor = new inT16[MAX_NUM_CLASSES];
CLASS_ID *ClassIdFor = new CLASS_ID[MAX_NUM_CLASSES];
CLASS_PRUNER_STRUCT **TempClassPruner =
new CLASS_PRUNER_STRUCT*[MAX_NUM_CLASS_PRUNERS];
uinT32 SetBitsForMask = // word with NUM_BITS_PER_CLASS
(1 << NUM_BITS_PER_CLASS) - 1; // set starting at bit 0
uinT32 Mask, NewMask, ClassBits;
int MaxNumConfigs = MAX_NUM_CONFIGS;
int WerdsPerConfigVec = WERDS_PER_CONFIG_VEC;
/* first read the high level template struct */
Templates = NewIntTemplates();
// Read Templates in parts for 64 bit compatibility.
if (fread(&unicharset_size, sizeof(int), 1, File) != 1)
cprintf("Bad read of inttemp!\n");
if (fread(&Templates->NumClasses,
sizeof(Templates->NumClasses), 1, File) != 1 ||
fread(&Templates->NumClassPruners,
sizeof(Templates->NumClassPruners), 1, File) != 1)
cprintf("Bad read of inttemp!\n");
// Swap status is determined automatically.
swap = Templates->NumClassPruners < 0 ||
Templates->NumClassPruners > MAX_NUM_CLASS_PRUNERS;
if (swap) {
Reverse32(&Templates->NumClassPruners);
Reverse32(&Templates->NumClasses);
Reverse32(&unicharset_size);
}
if (Templates->NumClasses < 0) {
// This file has a version id!
version_id = -Templates->NumClasses;
if (fread(&Templates->NumClasses, sizeof(Templates->NumClasses),
1, File) != 1)
cprintf("Bad read of inttemp!\n");
if (swap)
Reverse32(&Templates->NumClasses);
}
if (version_id < 3) {
MaxNumConfigs = OLD_MAX_NUM_CONFIGS;
WerdsPerConfigVec = OLD_WERDS_PER_CONFIG_VEC;
}
if (version_id < 2) {
for (i = 0; i < unicharset_size; ++i) {
if (fread(&IndexFor[i], sizeof(inT16), 1, File) != 1)
cprintf("Bad read of inttemp!\n");
}
for (i = 0; i < Templates->NumClasses; ++i) {
if (fread(&ClassIdFor[i], sizeof(CLASS_ID), 1, File) != 1)
cprintf("Bad read of inttemp!\n");
}
if (swap) {
for (i = 0; i < Templates->NumClasses; i++)
Reverse16(&IndexFor[i]);
for (i = 0; i < Templates->NumClasses; i++)
Reverse32(&ClassIdFor[i]);
}
}
/* then read in the class pruners */
for (i = 0; i < Templates->NumClassPruners; i++) {
Pruner = new CLASS_PRUNER_STRUCT;
if ((nread =
fread(Pruner, 1, sizeof(CLASS_PRUNER_STRUCT),
File)) != sizeof(CLASS_PRUNER_STRUCT))
cprintf("Bad read of inttemp!\n");
if (swap) {
for (x = 0; x < NUM_CP_BUCKETS; x++) {
for (y = 0; y < NUM_CP_BUCKETS; y++) {
for (z = 0; z < NUM_CP_BUCKETS; z++) {
for (w = 0; w < WERDS_PER_CP_VECTOR; w++) {
Reverse32(&Pruner->p[x][y][z][w]);
}
}
}
}
}
if (version_id < 2) {
TempClassPruner[i] = Pruner;
} else {
Templates->ClassPruners[i] = Pruner;
}
}
/* fix class pruners if they came from an old version of inttemp */
if (version_id < 2) {
// Allocate enough class pruners to cover all the class ids.
max_class_id = 0;
for (i = 0; i < Templates->NumClasses; i++)
if (ClassIdFor[i] > max_class_id)
max_class_id = ClassIdFor[i];
for (i = 0; i <= CPrunerIdFor(max_class_id); i++) {
Templates->ClassPruners[i] = new CLASS_PRUNER_STRUCT;
memset(Templates->ClassPruners[i], 0, sizeof(CLASS_PRUNER_STRUCT));
}
// Convert class pruners from the old format (indexed by class index)
// to the new format (indexed by class id).
last_cp_bit_number = NUM_BITS_PER_CLASS * Templates->NumClasses - 1;
for (i = 0; i < Templates->NumClassPruners; i++) {
for (x = 0; x < NUM_CP_BUCKETS; x++)
for (y = 0; y < NUM_CP_BUCKETS; y++)
for (z = 0; z < NUM_CP_BUCKETS; z++)
for (w = 0; w < WERDS_PER_CP_VECTOR; w++) {
if (TempClassPruner[i]->p[x][y][z][w] == 0)
continue;
for (b = 0; b < BITS_PER_WERD; b += NUM_BITS_PER_CLASS) {
bit_number = i * BITS_PER_CP_VECTOR + w * BITS_PER_WERD + b;
if (bit_number > last_cp_bit_number)
break; // the rest of the bits in this word are not used
class_id = ClassIdFor[bit_number / NUM_BITS_PER_CLASS];
// Single out NUM_BITS_PER_CLASS bits relating to class_id.
Mask = SetBitsForMask << b;
ClassBits = TempClassPruner[i]->p[x][y][z][w] & Mask;
// Move these bits to the new position in which they should
// appear (indexed corresponding to the class_id).
new_i = CPrunerIdFor(class_id);
new_w = CPrunerWordIndexFor(class_id);
new_b = CPrunerBitIndexFor(class_id) * NUM_BITS_PER_CLASS;
if (new_b > b) {
ClassBits <<= (new_b - b);
} else {
ClassBits >>= (b - new_b);
}
// Copy bits relating to class_id to the correct position
// in Templates->ClassPruner.
NewMask = SetBitsForMask << new_b;
Templates->ClassPruners[new_i]->p[x][y][z][new_w] &= ~NewMask;
Templates->ClassPruners[new_i]->p[x][y][z][new_w] |= ClassBits;
}
}
}
for (i = 0; i < Templates->NumClassPruners; i++) {
delete TempClassPruner[i];
}
}
/* then read in each class */
for (i = 0; i < Templates->NumClasses; i++) {
/* first read in the high level struct for the class */
Class = (INT_CLASS) Emalloc (sizeof (INT_CLASS_STRUCT));
if (fread(&Class->NumProtos, sizeof(Class->NumProtos), 1, File) != 1 ||
fread(&Class->NumProtoSets, sizeof(Class->NumProtoSets), 1, File) != 1 ||
fread(&Class->NumConfigs, sizeof(Class->NumConfigs), 1, File) != 1)
cprintf ("Bad read of inttemp!\n");
if (version_id == 0) {
// Only version 0 writes 5 pointless pointers to the file.
for (j = 0; j < 5; ++j) {
int junk;
if (fread(&junk, sizeof(junk), 1, File) != 1)
cprintf ("Bad read of inttemp!\n");
}
}
if (version_id < 4) {
for (j = 0; j < MaxNumConfigs; ++j) {
if (fread(&Class->ConfigLengths[j], sizeof(uinT16), 1, File) != 1)
cprintf ("Bad read of inttemp!\n");
}
if (swap) {
Reverse16(&Class->NumProtos);
for (j = 0; j < MaxNumConfigs; j++)
Reverse16(&Class->ConfigLengths[j]);
}
} else {
ASSERT_HOST(Class->NumConfigs < MaxNumConfigs);
for (j = 0; j < Class->NumConfigs; ++j) {
if (fread(&Class->ConfigLengths[j], sizeof(uinT16), 1, File) != 1)
cprintf ("Bad read of inttemp!\n");
}
if (swap) {
Reverse16(&Class->NumProtos);
for (j = 0; j < MaxNumConfigs; j++)
Reverse16(&Class->ConfigLengths[j]);
}
}
if (version_id < 2) {
ClassForClassId (Templates, ClassIdFor[i]) = Class;
} else {
ClassForClassId (Templates, i) = Class;
}
/* then read in the proto lengths */
Lengths = NULL;
if (MaxNumIntProtosIn (Class) > 0) {
Lengths = (uinT8 *)Emalloc(sizeof(uinT8) * MaxNumIntProtosIn(Class));
if ((nread =
fread((char *)Lengths, sizeof(uinT8),
MaxNumIntProtosIn(Class), File)) != MaxNumIntProtosIn (Class))
cprintf ("Bad read of inttemp!\n");
}
Class->ProtoLengths = Lengths;
/* then read in the proto sets */
for (j = 0; j < Class->NumProtoSets; j++) {
ProtoSet = (PROTO_SET)Emalloc(sizeof(PROTO_SET_STRUCT));
if (version_id < 3) {
if ((nread =
fread((char *) &ProtoSet->ProtoPruner, 1,
sizeof(PROTO_PRUNER), File)) != sizeof(PROTO_PRUNER))
cprintf("Bad read of inttemp!\n");
for (x = 0; x < PROTOS_PER_PROTO_SET; x++) {
if ((nread = fread((char *) &ProtoSet->Protos[x].A, 1,
sizeof(inT8), File)) != sizeof(inT8) ||
(nread = fread((char *) &ProtoSet->Protos[x].B, 1,
sizeof(uinT8), File)) != sizeof(uinT8) ||
(nread = fread((char *) &ProtoSet->Protos[x].C, 1,
sizeof(inT8), File)) != sizeof(inT8) ||
(nread = fread((char *) &ProtoSet->Protos[x].Angle, 1,
sizeof(uinT8), File)) != sizeof(uinT8))
cprintf("Bad read of inttemp!\n");
for (y = 0; y < WerdsPerConfigVec; y++)
if ((nread = fread((char *) &ProtoSet->Protos[x].Configs[y], 1,
sizeof(uinT32), File)) != sizeof(uinT32))
cprintf("Bad read of inttemp!\n");
}
} else {
if ((nread =
fread((char *) ProtoSet, 1, sizeof(PROTO_SET_STRUCT),
File)) != sizeof(PROTO_SET_STRUCT))
cprintf("Bad read of inttemp!\n");
}
if (swap) {
for (x = 0; x < NUM_PP_PARAMS; x++)
for (y = 0; y < NUM_PP_BUCKETS; y++)
for (z = 0; z < WERDS_PER_PP_VECTOR; z++)
Reverse32(&ProtoSet->ProtoPruner[x][y][z]);
for (x = 0; x < PROTOS_PER_PROTO_SET; x++)
for (y = 0; y < WerdsPerConfigVec; y++)
Reverse32(&ProtoSet->Protos[x].Configs[y]);
}
Class->ProtoSets[j] = ProtoSet;
}
if (version_id < 4)
Class->font_set_id = -1;
else {
fread(&Class->font_set_id, sizeof(int), 1, File);
if (swap)
Reverse32(&Class->font_set_id);
}
}
if (version_id < 2) {
/* add an empty NULL class with class id 0 */
assert(UnusedClassIdIn (Templates, 0));
ClassForClassId (Templates, 0) = NewIntClass (1, 1);
ClassForClassId (Templates, 0)->font_set_id = -1;
Templates->NumClasses++;
/* make sure the classes are contiguous */
for (i = 0; i < MAX_NUM_CLASSES; i++) {
if (i < Templates->NumClasses) {
if (ClassForClassId (Templates, i) == NULL) {
fprintf(stderr, "Non-contiguous class ids in inttemp\n");
exit(1);
}
} else {
if (ClassForClassId (Templates, i) != NULL) {
fprintf(stderr, "Class id %d exceeds NumClassesIn (Templates) %d\n",
i, Templates->NumClasses);
exit(1);
}
}
}
}
if (version_id >= 4) {
this->fontinfo_table_.read(File, NewPermanentTessCallback(read_info), swap);
if (version_id >= 5) {
this->fontinfo_table_.read(File,
NewPermanentTessCallback(read_spacing_info),
swap);
}
this->fontset_table_.read(File, NewPermanentTessCallback(read_set), swap);
}
// Clean up.
delete[] IndexFor;
delete[] ClassIdFor;
delete[] TempClassPruner;
return (Templates);
} /* ReadIntTemplates */
| void tesseract::Classify::ReadNewCutoffs | ( | FILE * | CutoffFile, |
| bool | swap, | ||
| inT64 | end_offset, | ||
| CLASS_CUTOFF_ARRAY | Cutoffs | ||
| ) |
Definition at line 42 of file cutoffs.cpp.
{
/*
** Parameters:
** Filename name of file containing cutoff definitions
** Cutoffs array to put cutoffs into
** Globals: none
** Operation: Open Filename, read in all of the class-id/cutoff pairs
** and insert them into the Cutoffs array. Cutoffs are
** indexed in the array by class id. Unused entries in the
** array are set to an arbitrarily high cutoff value.
** Return: none
** Exceptions: none
** History: Wed Feb 20 09:38:26 1991, DSJ, Created.
*/
char Class[UNICHAR_LEN + 1];
CLASS_ID ClassId;
int Cutoff;
int i;
if (shape_table_ != NULL) {
if (!shapetable_cutoffs_.DeSerialize(swap, CutoffFile)) {
tprintf("Error during read of shapetable pffmtable!\n");
}
}
for (i = 0; i < MAX_NUM_CLASSES; i++)
Cutoffs[i] = MAX_CUTOFF;
while ((end_offset < 0 || ftell(CutoffFile) < end_offset) &&
fscanf(CutoffFile, "%" REALLY_QUOTE_IT(UNICHAR_LEN) "s %d",
Class, &Cutoff) == 2) {
if (strcmp(Class, "NULL") == 0) {
ClassId = unicharset.unichar_to_id(" ");
} else {
ClassId = unicharset.unichar_to_id(Class);
}
Cutoffs[ClassId] = Cutoff;
SkipNewline(CutoffFile);
}
} /* ReadNewCutoffs */
| NORM_PROTOS * tesseract::Classify::ReadNormProtos | ( | FILE * | File, |
| inT64 | end_offset | ||
| ) |
Definition at line 230 of file normmatch.cpp.
{
/*
** Parameters:
** File open text file to read normalization protos from
** Globals: none
** Operation: This routine allocates a new data structure to hold
** a set of character normalization protos. It then fills in
** the data structure by reading from the specified File.
** Return: Character normalization protos.
** Exceptions: none
** History: Wed Dec 19 16:38:49 1990, DSJ, Created.
*/
NORM_PROTOS *NormProtos;
int i;
char unichar[2 * UNICHAR_LEN + 1];
UNICHAR_ID unichar_id;
LIST Protos;
int NumProtos;
/* allocate and initialization data structure */
NormProtos = (NORM_PROTOS *) Emalloc (sizeof (NORM_PROTOS));
NormProtos->NumProtos = unicharset.size();
NormProtos->Protos = (LIST *) Emalloc (NormProtos->NumProtos * sizeof(LIST));
for (i = 0; i < NormProtos->NumProtos; i++)
NormProtos->Protos[i] = NIL_LIST;
/* read file header and save in data structure */
NormProtos->NumParams = ReadSampleSize (File);
NormProtos->ParamDesc = ReadParamDesc (File, NormProtos->NumParams);
/* read protos for each class into a separate list */
while ((end_offset < 0 || ftell(File) < end_offset) &&
fscanf(File, "%s %d", unichar, &NumProtos) == 2) {
if (unicharset.contains_unichar(unichar)) {
unichar_id = unicharset.unichar_to_id(unichar);
Protos = NormProtos->Protos[unichar_id];
for (i = 0; i < NumProtos; i++)
Protos =
push_last (Protos, ReadPrototype (File, NormProtos->NumParams));
NormProtos->Protos[unichar_id] = Protos;
} else {
cprintf("Error: unichar %s in normproto file is not in unichar set.\n",
unichar);
for (i = 0; i < NumProtos; i++)
FreePrototype(ReadPrototype (File, NormProtos->NumParams));
}
SkipNewline(File);
}
return (NormProtos);
} /* ReadNormProtos */
| void tesseract::Classify::RefreshDebugWindow | ( | ScrollView ** | win, |
| const char * | msg, | ||
| int | y_offset, | ||
| const TBOX & | wbox | ||
| ) |
Definition at line 230 of file adaptmatch.cpp.
{
#ifndef GRAPHICS_DISABLED
const int kSampleSpaceWidth = 500;
if (*win == NULL) {
*win = new ScrollView(msg, 100, y_offset, kSampleSpaceWidth * 2, 200,
kSampleSpaceWidth * 2, 200, true);
}
(*win)->Clear();
(*win)->Pen(64, 64, 64);
(*win)->Line(-kSampleSpaceWidth, kBlnBaselineOffset,
kSampleSpaceWidth, kBlnBaselineOffset);
(*win)->Line(-kSampleSpaceWidth, kBlnXHeight + kBlnBaselineOffset,
kSampleSpaceWidth, kBlnXHeight + kBlnBaselineOffset);
(*win)->ZoomToRectangle(wbox.left(), wbox.top(),
wbox.right(), wbox.bottom());
#endif // GRAPHICS_DISABLED
}
| void tesseract::Classify::RemoveBadMatches | ( | ADAPT_RESULTS * | Results | ) |
This routine steps thru each matching class in Results and removes it from the match list if its rating is worse than the BestRating plus a pad. In other words, all good matches get moved to the front of the classes array.
| Results | contains matches to be filtered |
Globals:
Definition at line 2445 of file adaptmatch.cpp.
{
int Next, NextGood;
FLOAT32 BadMatchThreshold;
static const char* romans = "i v x I V X";
BadMatchThreshold = Results->best_match.rating + matcher_bad_match_pad;
if (classify_bln_numeric_mode) {
UNICHAR_ID unichar_id_one = unicharset.contains_unichar("1") ?
unicharset.unichar_to_id("1") : -1;
UNICHAR_ID unichar_id_zero = unicharset.contains_unichar("0") ?
unicharset.unichar_to_id("0") : -1;
ScoredClass scored_one = ScoredUnichar(Results, unichar_id_one);
ScoredClass scored_zero = ScoredUnichar(Results, unichar_id_zero);
for (Next = NextGood = 0; Next < Results->NumMatches; Next++) {
if (Results->match[Next].rating <= BadMatchThreshold) {
ScoredClass match = Results->match[Next];
if (!unicharset.get_isalpha(match.unichar_id) ||
strstr(romans,
unicharset.id_to_unichar(match.unichar_id)) != NULL) {
Results->match[NextGood++] = Results->match[Next];
} else if (unicharset.eq(match.unichar_id, "l") &&
scored_one.rating >= BadMatchThreshold) {
Results->match[NextGood] = scored_one;
Results->match[NextGood].rating = match.rating;
NextGood++;
} else if (unicharset.eq(match.unichar_id, "O") &&
scored_zero.rating >= BadMatchThreshold) {
Results->match[NextGood] = scored_zero;
Results->match[NextGood].rating = match.rating;
NextGood++;
}
}
}
} else {
for (Next = NextGood = 0; Next < Results->NumMatches; Next++) {
if (Results->match[Next].rating <= BadMatchThreshold)
Results->match[NextGood++] = Results->match[Next];
}
}
Results->NumMatches = NextGood;
} /* RemoveBadMatches */
| void tesseract::Classify::RemoveExtraPuncs | ( | ADAPT_RESULTS * | Results | ) |
This routine steps thru each matching class in Results and removes it from the match list if its rating is worse than the BestRating plus a pad. In other words, all good matches get moved to the front of the classes array.
| Results | contains matches to be filtered |
Globals:
Definition at line 2504 of file adaptmatch.cpp.
{
int Next, NextGood;
int punc_count; /*no of garbage characters */
int digit_count;
/*garbage characters */
static char punc_chars[] = ". , ; : / ` ~ ' - = \\ | \" ! _ ^";
static char digit_chars[] = "0 1 2 3 4 5 6 7 8 9";
punc_count = 0;
digit_count = 0;
for (Next = NextGood = 0; Next < Results->NumMatches; Next++) {
ScoredClass match = Results->match[Next];
if (strstr(punc_chars,
unicharset.id_to_unichar(match.unichar_id)) != NULL) {
if (punc_count < 2)
Results->match[NextGood++] = match;
punc_count++;
} else {
if (strstr(digit_chars,
unicharset.id_to_unichar(match.unichar_id)) != NULL) {
if (digit_count < 1)
Results->match[NextGood++] = match;
digit_count++;
} else {
Results->match[NextGood++] = match;
}
}
}
Results->NumMatches = NextGood;
} /* RemoveExtraPuncs */
| void tesseract::Classify::ResetAdaptiveClassifierInternal | ( | ) |
Definition at line 638 of file adaptmatch.cpp.
{
if (classify_learning_debug_level > 0) {
tprintf("Resetting adaptive classifier (NumAdaptationsFailed=%d)\n",
NumAdaptationsFailed);
}
free_adapted_templates(AdaptedTemplates);
AdaptedTemplates = NULL;
NumAdaptationsFailed = 0;
}
| void tesseract::Classify::ResetFeaturesHaveBeenExtracted | ( | ) |
Definition at line 1980 of file adaptmatch.cpp.
{
FeaturesHaveBeenExtracted = FALSE;
}
| void tesseract::Classify::SetAdaptiveThreshold | ( | FLOAT32 | Threshold | ) |
This routine resets the internal thresholds inside the integer matcher to correspond to the specified threshold.
| Threshold | threshold for creating new templates |
Globals:
Definition at line 2549 of file adaptmatch.cpp.
{
Threshold = (Threshold == matcher_good_threshold) ? 0.9: (1.0 - Threshold);
classify_adapt_proto_threshold.set_value(
ClipToRange<int>(255 * Threshold, 0, 255));
classify_adapt_feature_threshold.set_value(
ClipToRange<int>(255 * Threshold, 0, 255));
} /* SetAdaptiveThreshold */
| void tesseract::Classify::SettupPass1 | ( | ) |
This routine prepares the adaptive matcher for the start of the first pass. Learning is enabled (unless it is disabled for the whole program).
Globals:
Definition at line 712 of file adaptmatch.cpp.
{
EnableLearning = classify_enable_learning;
getDict().SettupStopperPass1();
} /* SettupPass1 */
| void tesseract::Classify::SettupPass2 | ( | ) |
This routine prepares the adaptive matcher for the start of the second pass. Further learning is disabled.
Globals:
Definition at line 732 of file adaptmatch.cpp.
{
EnableLearning = FALSE;
getDict().SettupStopperPass2();
} /* SettupPass2 */
| const ShapeTable* tesseract::Classify::shape_table | ( | ) | const [inline] |
Definition at line 66 of file classify.h.
{
return shape_table_;
}
| int tesseract::Classify::ShapeIDToClassID | ( | int | shape_id | ) | const |
Definition at line 2747 of file adaptmatch.cpp.
{
for (int id = 0; id < PreTrainedTemplates->NumClasses; ++id) {
int font_set_id = PreTrainedTemplates->Class[id]->font_set_id;
ASSERT_HOST(font_set_id >= 0);
const FontSet &fs = fontset_table_.get(font_set_id);
for (int config = 0; config < fs.size; ++config) {
if (fs.configs[config] == shape_id)
return id;
}
}
tprintf("Shape %d not found\n", shape_id);
return -1;
}
| void tesseract::Classify::ShowBestMatchFor | ( | TBLOB * | Blob, |
| const DENORM & | denorm, | ||
| CLASS_ID | ClassId, | ||
| int | shape_id, | ||
| BOOL8 | AdaptiveOn, | ||
| BOOL8 | PreTrainedOn, | ||
| ADAPT_RESULTS * | Results | ||
| ) |
This routine compares Blob to both sets of templates (adaptive and pre-trained) and then displays debug information for the config which matched best.
| Blob | blob to show best matching config for |
| denorm | normalization/denormalization parameters |
| ClassId | class whose configs are to be searched |
| shape_id | shape index |
| AdaptiveOn | TRUE if adaptive configs are enabled |
| PreTrainedOn | TRUE if pretrained configs are enabled |
| Results | results of match being debugged |
Globals:
Definition at line 2580 of file adaptmatch.cpp.
{
int NumCNFeatures = 0, NumBLFeatures = 0;
INT_FEATURE_ARRAY CNFeatures, BLFeatures;
INT_RESULT_STRUCT CNResult, BLResult;
inT32 BlobLength;
uinT32 ConfigMask;
static int next_config = -1;
if (PreTrainedOn) next_config = -1;
CNResult.Rating = BLResult.Rating = 2.0;
if (!LegalClassId (ClassId)) {
cprintf ("%d is not a legal class id!!\n", ClassId);
return;
}
uinT8 *CNAdjust = new uinT8[MAX_NUM_CLASSES];
uinT8 *BLAdjust = new uinT8[MAX_NUM_CLASSES];
if (shape_table_ == NULL)
shape_id = ClassId;
else
shape_id = ShapeIDToClassID(shape_id);
if (PreTrainedOn && shape_id >= 0) {
if (UnusedClassIdIn(PreTrainedTemplates, shape_id)) {
tprintf("No built-in templates for class/shape %d\n", shape_id);
} else {
NumCNFeatures = GetCharNormFeatures(Blob, denorm, PreTrainedTemplates,
CNFeatures, NULL, CNAdjust,
&BlobLength, NULL);
if (NumCNFeatures <= 0) {
tprintf("Illegal blob (char norm features)!\n");
} else {
im_.SetCharNormMatch(classify_integer_matcher_multiplier);
im_.Match(ClassForClassId(PreTrainedTemplates, shape_id),
AllProtosOn, AllConfigsOn,
NumCNFeatures, CNFeatures,
&CNResult,
classify_adapt_feature_threshold, NO_DEBUG,
matcher_debug_separate_windows);
ExpandShapesAndApplyCorrections(NULL, false, shape_id,
Blob->bounding_box().bottom(),
Blob->bounding_box().top(),
0, BlobLength, CNAdjust,
CNResult, Results);
}
}
}
if (AdaptiveOn) {
if (ClassId < 0 || ClassId >= AdaptedTemplates->Templates->NumClasses) {
tprintf("Invalid adapted class id: %d\n", ClassId);
} else if (UnusedClassIdIn(AdaptedTemplates->Templates, ClassId) ||
AdaptedTemplates->Class[ClassId] == NULL ||
IsEmptyAdaptedClass(AdaptedTemplates->Class[ClassId])) {
tprintf("No AD templates for class %d = %s\n",
ClassId, unicharset.id_to_unichar(ClassId));
} else {
NumBLFeatures = GetBaselineFeatures(Blob,
denorm,
AdaptedTemplates->Templates,
BLFeatures, BLAdjust,
&BlobLength);
if (NumBLFeatures <= 0)
tprintf("Illegal blob (baseline features)!\n");
else {
im_.SetBaseLineMatch();
im_.Match(ClassForClassId(AdaptedTemplates->Templates, ClassId),
AllProtosOn, AllConfigsOn,
NumBLFeatures, BLFeatures,
&BLResult,
classify_adapt_feature_threshold, NO_DEBUG,
matcher_debug_separate_windows);
ExpandShapesAndApplyCorrections(
AdaptedTemplates->Class, false,
ClassId, Blob->bounding_box().bottom(),
Blob->bounding_box().top(), 0, BlobLength, CNAdjust,
BLResult, Results);
}
}
}
tprintf("\n");
if (BLResult.Rating < CNResult.Rating) {
if (next_config < 0) {
ConfigMask = 1 << BLResult.Config;
next_config = 0;
} else {
ConfigMask = 1 << next_config;
++next_config;
}
classify_norm_method.set_value(baseline);
im_.SetBaseLineMatch();
tprintf("Adaptive Class ID: %d\n", ClassId);
im_.Match(ClassForClassId(AdaptedTemplates->Templates, ClassId),
AllProtosOn, (BIT_VECTOR) &ConfigMask,
NumBLFeatures, BLFeatures,
&BLResult,
classify_adapt_feature_threshold,
matcher_debug_flags,
matcher_debug_separate_windows);
ExpandShapesAndApplyCorrections(
AdaptedTemplates->Class, true,
ClassId, Blob->bounding_box().bottom(),
Blob->bounding_box().top(), 0, BlobLength, CNAdjust,
BLResult, Results);
} else if (shape_id >= 0) {
ConfigMask = 1 << CNResult.Config;
classify_norm_method.set_value(character);
tprintf("Static Shape ID: %d\n", shape_id);
im_.SetCharNormMatch(classify_integer_matcher_multiplier);
im_.Match(ClassForClassId (PreTrainedTemplates, shape_id),
AllProtosOn, (BIT_VECTOR) & ConfigMask,
NumCNFeatures, CNFeatures,
&CNResult,
classify_adapt_feature_threshold,
matcher_debug_flags,
matcher_debug_separate_windows);
ExpandShapesAndApplyCorrections(NULL, true, shape_id,
Blob->bounding_box().bottom(),
Blob->bounding_box().top(),
0, BlobLength, CNAdjust,
CNResult, Results);
}
// Clean up.
delete[] CNAdjust;
delete[] BLAdjust;
} /* ShowBestMatchFor */
| void tesseract::Classify::ShowMatchDisplay | ( | ) |
Definition at line 1096 of file intproto.cpp.
{
/*
** Parameters: none
** Globals:
** FeatureShapes display list containing feature matches
** ProtoShapes display list containing proto matches
** Operation: This routine sends the shapes in the global display
** lists to the match debugger window.
** Return: none
** Exceptions: none
** History: Thu Mar 21 15:47:33 1991, DSJ, Created.
*/
InitIntMatchWindowIfReqd();
if (ProtoDisplayWindow) {
ProtoDisplayWindow->Clear();
}
if (FeatureDisplayWindow) {
FeatureDisplayWindow->Clear();
}
ClearFeatureSpaceWindow(
static_cast<NORM_METHOD>(static_cast<int>(classify_norm_method)),
IntMatchWindow);
IntMatchWindow->ZoomToRectangle(INT_MIN_X, INT_MIN_Y,
INT_MAX_X, INT_MAX_Y);
if (ProtoDisplayWindow) {
ProtoDisplayWindow->ZoomToRectangle(INT_MIN_X, INT_MIN_Y,
INT_MAX_X, INT_MAX_Y);
}
if (FeatureDisplayWindow) {
FeatureDisplayWindow->ZoomToRectangle(INT_MIN_X, INT_MIN_Y,
INT_MAX_X, INT_MAX_Y);
}
} /* ShowMatchDisplay */
| bool tesseract::Classify::TempConfigReliable | ( | CLASS_ID | class_id, |
| const TEMP_CONFIG & | config | ||
| ) |
Definition at line 2763 of file adaptmatch.cpp.
{
if (classify_learning_debug_level >= 1) {
tprintf("NumTimesSeen for config of %s is %d\n",
getDict().getUnicharset().debug_str(class_id).string(),
config->NumTimesSeen);
}
if (config->NumTimesSeen >= matcher_sufficient_examples_for_prototyping) {
return true;
} else if (config->NumTimesSeen < matcher_min_examples_for_prototyping) {
return false;
} else if (use_ambigs_for_adaption) {
// Go through the ambigs vector and see whether we have already seen
// enough times all the characters represented by the ambigs vector.
const UnicharIdVector *ambigs =
getDict().getUnicharAmbigs().AmbigsForAdaption(class_id);
int ambigs_size = (ambigs == NULL) ? 0 : ambigs->size();
for (int ambig = 0; ambig < ambigs_size; ++ambig) {
ADAPT_CLASS ambig_class = AdaptedTemplates->Class[(*ambigs)[ambig]];
assert(ambig_class != NULL);
if (ambig_class->NumPermConfigs == 0 &&
ambig_class->MaxNumTimesSeen <
matcher_min_examples_for_prototyping) {
if (classify_learning_debug_level >= 1) {
tprintf("Ambig %s has not been seen enough times,"
" not making config for %s permanent\n",
getDict().getUnicharset().debug_str(
(*ambigs)[ambig]).string(),
getDict().getUnicharset().debug_str(class_id).string());
}
return false;
}
}
}
return true;
}
| void tesseract::Classify::UpdateAmbigsGroup | ( | CLASS_ID | class_id, |
| const DENORM & | denorm, | ||
| TBLOB * | Blob | ||
| ) |
Definition at line 2800 of file adaptmatch.cpp.
{
const UnicharIdVector *ambigs =
getDict().getUnicharAmbigs().ReverseAmbigsForAdaption(class_id);
int ambigs_size = (ambigs == NULL) ? 0 : ambigs->size();
if (classify_learning_debug_level >= 1) {
tprintf("Running UpdateAmbigsGroup for %s class_id=%d\n",
getDict().getUnicharset().debug_str(class_id).string(), class_id);
}
for (int ambig = 0; ambig < ambigs_size; ++ambig) {
CLASS_ID ambig_class_id = (*ambigs)[ambig];
const ADAPT_CLASS ambigs_class = AdaptedTemplates->Class[ambig_class_id];
for (int cfg = 0; cfg < MAX_NUM_CONFIGS; ++cfg) {
if (ConfigIsPermanent(ambigs_class, cfg)) continue;
const TEMP_CONFIG config =
TempConfigFor(AdaptedTemplates->Class[ambig_class_id], cfg);
if (config != NULL && TempConfigReliable(ambig_class_id, config)) {
if (classify_learning_debug_level >= 1) {
tprintf("Making config %d of %s permanent\n", cfg,
getDict().getUnicharset().debug_str(
ambig_class_id).string());
}
MakePermanent(AdaptedTemplates, ambig_class_id, cfg, denorm, Blob);
}
}
}
}
| void tesseract::Classify::WriteAdaptedTemplates | ( | FILE * | File, |
| ADAPT_TEMPLATES | Templates | ||
| ) |
This routine saves Templates to File in a binary format.
| File | open text file to write Templates to |
| Templates | set of adapted templates to write to File |
Definition at line 507 of file adaptive.cpp.
{
int i;
/* first write the high level adaptive template struct */
fwrite ((char *) Templates, sizeof (ADAPT_TEMPLATES_STRUCT), 1, File);
/* then write out the basic integer templates */
WriteIntTemplates (File, Templates->Templates, unicharset);
/* then write out the adaptive info for each class */
for (i = 0; i < (Templates->Templates)->NumClasses; i++) {
WriteAdaptedClass (File, Templates->Class[i],
Templates->Templates->Class[i]->NumConfigs);
}
} /* WriteAdaptedTemplates */
| void tesseract::Classify::WriteIntTemplates | ( | FILE * | File, |
| INT_TEMPLATES | Templates, | ||
| const UNICHARSET & | target_unicharset | ||
| ) |
Definition at line 1155 of file intproto.cpp.
{
/*
** Parameters:
** File open file to write templates to
** Templates templates to save into File
** Globals: none
** Operation: This routine writes Templates to File. The format
** is an efficient binary format. File must already be open
** for writing.
** Return: none
** Exceptions: none
** History: Wed Feb 27 11:48:46 1991, DSJ, Created.
*/
int i, j;
INT_CLASS Class;
int unicharset_size = target_unicharset.size();
int version_id = -5; // When negated by the reader -1 becomes +1 etc.
if (Templates->NumClasses != unicharset_size) {
cprintf("Warning: executing WriteIntTemplates() with %d classes in"
" Templates, while target_unicharset size is %d\n",
Templates->NumClasses, unicharset_size);
}
/* first write the high level template struct */
fwrite(&unicharset_size, sizeof(unicharset_size), 1, File);
fwrite(&version_id, sizeof(version_id), 1, File);
fwrite(&Templates->NumClassPruners, sizeof(Templates->NumClassPruners),
1, File);
fwrite(&Templates->NumClasses, sizeof(Templates->NumClasses), 1, File);
/* then write out the class pruners */
for (i = 0; i < Templates->NumClassPruners; i++)
fwrite(Templates->ClassPruners[i],
sizeof(CLASS_PRUNER_STRUCT), 1, File);
/* then write out each class */
for (i = 0; i < Templates->NumClasses; i++) {
Class = Templates->Class[i];
/* first write out the high level struct for the class */
fwrite(&Class->NumProtos, sizeof(Class->NumProtos), 1, File);
fwrite(&Class->NumProtoSets, sizeof(Class->NumProtoSets), 1, File);
ASSERT_HOST(Class->NumConfigs == this->fontset_table_.get(Class->font_set_id).size);
fwrite(&Class->NumConfigs, sizeof(Class->NumConfigs), 1, File);
for (j = 0; j < Class->NumConfigs; ++j) {
fwrite(&Class->ConfigLengths[j], sizeof(uinT16), 1, File);
}
/* then write out the proto lengths */
if (MaxNumIntProtosIn (Class) > 0) {
fwrite ((char *) (Class->ProtoLengths), sizeof (uinT8),
MaxNumIntProtosIn (Class), File);
}
/* then write out the proto sets */
for (j = 0; j < Class->NumProtoSets; j++)
fwrite ((char *) Class->ProtoSets[j],
sizeof (PROTO_SET_STRUCT), 1, File);
/* then write the fonts info */
fwrite(&Class->font_set_id, sizeof(int), 1, File);
}
/* Write the fonts info tables */
this->fontinfo_table_.write(File, NewPermanentTessCallback(write_info));
this->fontinfo_table_.write(File,
NewPermanentTessCallback(write_spacing_info));
this->fontset_table_.write(File, NewPermanentTessCallback(write_set));
} /* WriteIntTemplates */
Definition at line 430 of file classify.h.
Definition at line 437 of file classify.h.
Definition at line 435 of file classify.h.
Definition at line 436 of file classify.h.
Definition at line 433 of file classify.h.
| double tesseract::Classify::certainty_scale = 20.0 |
"Certainty scaling factor"
Definition at line 398 of file classify.h.
"Threshold for good features during adaptive 0-255"
Definition at line 404 of file classify.h.
"Threshold for good protos during adaptive 0-255"
Definition at line 402 of file classify.h.
"Assume the input is numbers [0-9]."
Definition at line 455 of file classify.h.
| double tesseract::Classify::classify_char_norm_range = 0.2 |
"Character Normalization Range ..."
Definition at line 363 of file classify.h.
"Exclude fragments that do not match any whole character" " with at least this certainty"
Definition at line 410 of file classify.h.
"Class Pruner Multiplier 0-255: "
Definition at line 422 of file classify.h.
"Class Pruner Threshold 0-255"
Definition at line 420 of file classify.h.
"Class Pruner CutoffStrength: "
Definition at line 424 of file classify.h.
"Bring up graphical debugging windows for fragments training"
Definition at line 412 of file classify.h.
"Classify debug level"
Definition at line 357 of file classify.h.
"Enable match debugger"
Definition at line 377 of file classify.h.
"Enable adaptive classifier"
Definition at line 372 of file classify.h.
| bool tesseract::Classify::classify_enable_learning = true |
"Enable adaptive classifier"
Definition at line 356 of file classify.h.
"Integer Matcher Multiplier 0-255: "
Definition at line 426 of file classify.h.
"Class str to debug learning"
Definition at line 416 of file classify.h.
"Learning Debug Level: "
Definition at line 380 of file classify.h.
| double tesseract::Classify::classify_max_norm_scale_x = 0.325 |
"Max char x-norm scale ..."
Definition at line 365 of file classify.h.
| double tesseract::Classify::classify_max_norm_scale_y = 0.325 |
"Max char y-norm scale ..."
Definition at line 367 of file classify.h.
| double tesseract::Classify::classify_min_norm_scale_x = 0.0 |
"Min char x-norm scale ..."
Definition at line 364 of file classify.h.
| double tesseract::Classify::classify_min_norm_scale_y = 0.0 |
"Min char y-norm scale ..."
Definition at line 366 of file classify.h.
| double tesseract::Classify::classify_misfit_junk_penalty = 0.0 |
"Penalty to apply when a non-alnum is vertically out of " "its expected textline position"
Definition at line 396 of file classify.h.
| int tesseract::Classify::classify_norm_method = character |
"Normalization Method ..."
Definition at line 361 of file classify.h.
"Save adapted templates to a file"
Definition at line 376 of file classify.h.
"Use pre-adapted classifier templates"
Definition at line 374 of file classify.h.
"Do not include character fragments in the" " results of the classifier"
Definition at line 407 of file classify.h.
Definition at line 439 of file classify.h.
Definition at line 459 of file classify.h.
Definition at line 443 of file classify.h.
Definition at line 451 of file classify.h.
"Dont adapt to i/I at beginning of word"
Definition at line 453 of file classify.h.
IntegerMatcher tesseract::Classify::im_ [protected] |
Definition at line 455 of file classify.h.
| double tesseract::Classify::matcher_avg_noise_size = 12.0 |
"Avg. noise blob length: "
Definition at line 386 of file classify.h.
| double tesseract::Classify::matcher_bad_match_pad = 0.15 |
"Bad Match Pad (0-1)"
Definition at line 384 of file classify.h.
| double tesseract::Classify::matcher_clustering_max_angle_delta = 0.015 |
"Maximum angle delta for prototype clustering"
Definition at line 393 of file classify.h.
"Matcher Debug Flags"
Definition at line 379 of file classify.h.
"Matcher Debug Level"
Definition at line 378 of file classify.h.
"Use two different windows for debugging the matching: " "One for the protos and one for the features."
Definition at line 415 of file classify.h.
| double tesseract::Classify::matcher_good_threshold = 0.125 |
"Good Match (0-1)"
Definition at line 381 of file classify.h.
| double tesseract::Classify::matcher_great_threshold = 0.0 |
"Great Match (0-1)"
Definition at line 382 of file classify.h.
"Reliable Config Threshold"
Definition at line 389 of file classify.h.
| double tesseract::Classify::matcher_perfect_threshold = 0.02 |
"Perfect Match (0-1)"
Definition at line 383 of file classify.h.
"Min # of permanent classes"
Definition at line 387 of file classify.h.
| double tesseract::Classify::matcher_rating_margin = 0.1 |
"New template margin (0-1)"
Definition at line 385 of file classify.h.
"Enable adaption even if the ambiguities have not been seen"
Definition at line 391 of file classify.h.
Definition at line 441 of file classify.h.
Definition at line 426 of file classify.h.
"Prioritize blob division over chopping"
Definition at line 354 of file classify.h.
Definition at line 434 of file classify.h.
| double tesseract::Classify::rating_scale = 1.5 |
"Rating scaling factor"
Definition at line 397 of file classify.h.
ShapeTable* tesseract::Classify::shape_table_ [protected] |
Definition at line 464 of file classify.h.
Definition at line 438 of file classify.h.
"Baseline Normalized Matching"
Definition at line 371 of file classify.h.
"Character Normalized Matching"
Definition at line 370 of file classify.h.
| double tesseract::Classify::tessedit_class_miss_scale = 0.00390625 |
"Scale factor for features not used"
Definition at line 400 of file classify.h.
"Top choice only from CP"
Definition at line 355 of file classify.h.
1.7.5.1