Tesseract  3.02
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
tesseract::ClassPruner Class Reference

List of all members.

Public Member Functions

 ClassPruner (int max_classes)
 ~ClassPruner ()
void ComputeScores (const INT_TEMPLATES_STRUCT *int_templates, int num_features, const INT_FEATURE_STRUCT *features)
void AdjustForExpectedNumFeatures (const uinT16 *expected_num_features, int cutoff_strength)
void DisableDisabledClasses (const UNICHARSET &unicharset)
void DisableFragments (const UNICHARSET &unicharset)
void NormalizeForXheight (int norm_multiplier, const uinT8 *normalization_factors)
void NoNormalization ()
void PruneAndSort (int pruning_factor, bool max_of_non_fragments, const UNICHARSET &unicharset)
void DebugMatch (const Classify &classify, const INT_TEMPLATES_STRUCT *int_templates, const INT_FEATURE_STRUCT *features) const
void SummarizeResult (const Classify &classify, const INT_TEMPLATES_STRUCT *int_templates, const uinT16 *expected_num_features, int norm_multiplier, const uinT8 *normalization_factors) const
int SetupResults (CP_RESULT_STRUCT *results) const

Detailed Description

Definition at line 109 of file intmatcher.cpp.


Constructor & Destructor Documentation

tesseract::ClassPruner::ClassPruner ( int  max_classes)
inline

Definition at line 111 of file intmatcher.cpp.

{
// The unrolled loop in ComputeScores means that the array sizes need to
// be rounded up so that the array is big enough to accommodate the extra
// entries accessed by the unrolling. Each pruner word is of sized
// BITS_PER_WERD and each entry is NUM_BITS_PER_CLASS, so there are
// BITS_PER_WERD / NUM_BITS_PER_CLASS entries.
// See ComputeScores.
max_classes_ = max_classes;
rounded_classes_ = RoundUp(
class_count_ = new int[rounded_classes_];
norm_count_ = new int[rounded_classes_];
sort_key_ = new int[rounded_classes_ + 1];
sort_index_ = new int[rounded_classes_ + 1];
for (int i = 0; i < rounded_classes_; i++) {
class_count_[i] = 0;
}
pruning_threshold_ = 0;
num_features_ = 0;
num_classes_ = 0;
}
tesseract::ClassPruner::~ClassPruner ( )
inline

Definition at line 133 of file intmatcher.cpp.

{
delete []class_count_;
delete []norm_count_;
delete []sort_key_;
delete []sort_index_;
}

Member Function Documentation

void tesseract::ClassPruner::AdjustForExpectedNumFeatures ( const uinT16 expected_num_features,
int  cutoff_strength 
)
inline

Definition at line 213 of file intmatcher.cpp.

{
for (int class_id = 0; class_id < max_classes_; ++class_id) {
if (num_features_ < expected_num_features[class_id]) {
int deficit = expected_num_features[class_id] - num_features_;
class_count_[class_id] -= class_count_[class_id] * deficit /
(num_features_ * cutoff_strength + deficit);
}
}
}
void tesseract::ClassPruner::ComputeScores ( const INT_TEMPLATES_STRUCT int_templates,
int  num_features,
const INT_FEATURE_STRUCT features 
)
inline

Definition at line 142 of file intmatcher.cpp.

{
num_features_ = num_features;
int num_pruners = int_templates->NumClassPruners;
for (int f = 0; f < num_features; ++f) {
const INT_FEATURE_STRUCT* feature = &features[f];
// Quantize the feature to NUM_CP_BUCKETS*NUM_CP_BUCKETS*NUM_CP_BUCKETS.
int x = feature->X * NUM_CP_BUCKETS >> 8;
int y = feature->Y * NUM_CP_BUCKETS >> 8;
int theta = feature->Theta * NUM_CP_BUCKETS >> 8;
int class_id = 0;
// Each CLASS_PRUNER_STRUCT only covers CLASSES_PER_CP(32) classes, so
// we need a collection of them, indexed by pruner_set.
for (int pruner_set = 0; pruner_set < num_pruners; ++pruner_set) {
// Look up quantized feature in a 3-D array, an array of weights for
// each class.
const uinT32* pruner_word_ptr =
int_templates->ClassPruners[pruner_set]->p[x][y][theta];
for (int word = 0; word < WERDS_PER_CP_VECTOR; ++word) {
uinT32 pruner_word = *pruner_word_ptr++;
// This inner loop is unrolled to speed up the ClassPruner.
// Currently gcc would not unroll it unless it is set to O3
// level of optimization or -funroll-loops is specified.
/*
uinT32 class_mask = (1 << NUM_BITS_PER_CLASS) - 1;
for (int bit = 0; bit < BITS_PER_WERD/NUM_BITS_PER_CLASS; bit++) {
class_count_[class_id++] += pruner_word & class_mask;
pruner_word >>= NUM_BITS_PER_CLASS;
}
*/
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
pruner_word >>= NUM_BITS_PER_CLASS;
class_count_[class_id++] += pruner_word & CLASS_PRUNER_CLASS_MASK;
}
}
}
}
void tesseract::ClassPruner::DebugMatch ( const Classify classify,
const INT_TEMPLATES_STRUCT int_templates,
const INT_FEATURE_STRUCT features 
) const
inline

Definition at line 300 of file intmatcher.cpp.

{
int num_pruners = int_templates->NumClassPruners;
int max_num_classes = int_templates->NumClasses;
for (int f = 0; f < num_features_; ++f) {
const INT_FEATURE_STRUCT* feature = &features[f];
tprintf("F=%3d(%d,%d,%d),", f, feature->X, feature->Y, feature->Theta);
// Quantize the feature to NUM_CP_BUCKETS*NUM_CP_BUCKETS*NUM_CP_BUCKETS.
int x = feature->X * NUM_CP_BUCKETS >> 8;
int y = feature->Y * NUM_CP_BUCKETS >> 8;
int theta = feature->Theta * NUM_CP_BUCKETS >> 8;
int class_id = 0;
for (int pruner_set = 0; pruner_set < num_pruners; ++pruner_set) {
// Look up quantized feature in a 3-D array, an array of weights for
// each class.
const uinT32* pruner_word_ptr =
int_templates->ClassPruners[pruner_set]->p[x][y][theta];
for (int word = 0; word < WERDS_PER_CP_VECTOR; ++word) {
uinT32 pruner_word = *pruner_word_ptr++;
for (int word_class = 0; word_class < 16 &&
class_id < max_num_classes; ++word_class, ++class_id) {
if (norm_count_[class_id] >= pruning_threshold_) {
tprintf(" %s=%d,",
classify.ClassIDToDebugStr(int_templates,
class_id, 0).string(),
pruner_word & CLASS_PRUNER_CLASS_MASK);
}
pruner_word >>= NUM_BITS_PER_CLASS;
}
}
tprintf("\n");
}
}
}
void tesseract::ClassPruner::DisableDisabledClasses ( const UNICHARSET unicharset)
inline

Definition at line 226 of file intmatcher.cpp.

{
for (int class_id = 0; class_id < max_classes_; ++class_id) {
if (!unicharset.get_enabled(class_id))
class_count_[class_id] = 0; // This char is disabled!
}
}
void tesseract::ClassPruner::DisableFragments ( const UNICHARSET unicharset)
inline

Definition at line 234 of file intmatcher.cpp.

{
for (int class_id = 0; class_id < max_classes_; ++class_id) {
// Do not include character fragments in the class pruner
// results if disable_character_fragments is true.
if (unicharset.get_fragment(class_id)) {
class_count_[class_id] = 0;
}
}
}
void tesseract::ClassPruner::NoNormalization ( )
inline

Definition at line 257 of file intmatcher.cpp.

{
for (int class_id = 0; class_id < max_classes_; class_id++) {
norm_count_[class_id] = class_count_[class_id];
}
}
void tesseract::ClassPruner::NormalizeForXheight ( int  norm_multiplier,
const uinT8 normalization_factors 
)
inline

Definition at line 248 of file intmatcher.cpp.

{
for (int class_id = 0; class_id < max_classes_; class_id++) {
norm_count_[class_id] = class_count_[class_id] -
((norm_multiplier * normalization_factors[class_id]) >> 8);
}
}
void tesseract::ClassPruner::PruneAndSort ( int  pruning_factor,
bool  max_of_non_fragments,
const UNICHARSET unicharset 
)
inline

Definition at line 266 of file intmatcher.cpp.

{
int max_count = 0;
for (int c = 0; c < max_classes_; ++c) {
if (norm_count_[c] > max_count &&
// This additional check is added in order to ensure that
// the classifier will return at least one non-fragmented
// character match.
// TODO(daria): verify that this helps accuracy and does not
// hurt performance.
(!max_of_non_fragments || !unicharset.get_fragment(c))) {
max_count = norm_count_[c];
}
}
// Prune Classes.
pruning_threshold_ = (max_count * pruning_factor) >> 8;
// Select Classes.
if (pruning_threshold_ < 1)
pruning_threshold_ = 1;
num_classes_ = 0;
for (int class_id = 0; class_id < max_classes_; class_id++) {
if (norm_count_[class_id] >= pruning_threshold_) {
++num_classes_;
sort_index_[num_classes_] = class_id;
sort_key_[num_classes_] = norm_count_[class_id];
}
}
// Sort Classes using Heapsort Algorithm.
if (num_classes_ > 1)
HeapSort(num_classes_, sort_key_, sort_index_);
}
int tesseract::ClassPruner::SetupResults ( CP_RESULT_STRUCT results) const
inline

Definition at line 360 of file intmatcher.cpp.

{
for (int c = 0; c < num_classes_; ++c) {
results[c].Class = sort_index_[num_classes_ - c];
results[c].Rating = 1.0 - sort_key_[num_classes_ - c] /
(static_cast<float>(CLASS_PRUNER_CLASS_MASK) * num_features_);
}
return num_classes_;
}
void tesseract::ClassPruner::SummarizeResult ( const Classify classify,
const INT_TEMPLATES_STRUCT int_templates,
const uinT16 expected_num_features,
int  norm_multiplier,
const uinT8 normalization_factors 
) const
inline

Definition at line 337 of file intmatcher.cpp.

{
tprintf("CP:%d classes, %d features:\n", num_classes_, num_features_);
for (int i = 0; i < num_classes_; ++i) {
int class_id = sort_index_[num_classes_ - i];
STRING class_string = classify.ClassIDToDebugStr(int_templates,
class_id, 0);
tprintf("%s:Initial=%d, E=%d, Xht-adj=%d, N=%d, Rat=%.2f\n",
class_string.string(),
class_count_[class_id],
expected_num_features[class_id],
(norm_multiplier * normalization_factors[class_id]) >> 8,
sort_key_[num_classes_ - i],
100.0 - 100.0 * sort_key_[num_classes_ - i] /
(CLASS_PRUNER_CLASS_MASK * num_features_));
}
}

The documentation for this class was generated from the following file: