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

#include <trainingsample.h>

Inheritance diagram for tesseract::TrainingSample:
ELIST_LINK

List of all members.

Public Member Functions

 TrainingSample ()
 ~TrainingSample ()
TrainingSampleRandomizedCopy (int index) const
TrainingSampleCopy () const
bool Serialize (FILE *fp) const
bool DeSerialize (bool swap, FILE *fp)
void ExtractCharDesc (int feature_type, int micro_type, int cn_type, int geo_type, CHAR_DESC_STRUCT *char_desc)
void IndexFeatures (const IntFeatureSpace &feature_space)
void MapFeatures (const IntFeatureMap &feature_map)
Pix * RenderToPix (const UNICHARSET *unicharset) const
void DisplayFeatures (ScrollView::Color color, ScrollView *window) const
Pix * GetSamplePix (int padding, Pix *page_pix) const
UNICHAR_ID class_id () const
void set_class_id (int id)
int font_id () const
void set_font_id (int id)
int page_num () const
void set_page_num (int page)
const TBOXbounding_box () const
void set_bounding_box (const TBOX &box)
int num_features () const
const INT_FEATURE_STRUCTfeatures () const
int num_micro_features () const
const MicroFeaturemicro_features () const
float cn_feature (int index) const
int geo_feature (int index) const
double weight () const
void set_weight (double value)
double max_dist () const
void set_max_dist (double value)
int sample_index () const
void set_sample_index (int value)
bool features_are_mapped () const
const GenericVector< int > & mapped_features () const
const GenericVector< int > & indexed_features () const
bool is_error () const
void set_is_error (bool value)
- Public Member Functions inherited from ELIST_LINK
 ELIST_LINK ()
 ELIST_LINK (const ELIST_LINK &)
void operator= (const ELIST_LINK &)

Static Public Member Functions

static TrainingSampleCopyFromFeatures (const INT_FX_RESULT_STRUCT &fx_info, const INT_FEATURE_STRUCT *features, int num_features)
static TrainingSampleDeSerializeCreate (bool swap, FILE *fp)

Detailed Description

Definition at line 53 of file trainingsample.h.


Constructor & Destructor Documentation

tesseract::TrainingSample::TrainingSample ( )
inline

Definition at line 55 of file trainingsample.h.

: class_id_(INVALID_UNICHAR_ID), font_id_(0), page_num_(0),
num_features_(0), num_micro_features_(0),
features_(NULL), micro_features_(NULL), weight_(1.0),
max_dist_(0.0), sample_index_(0),
features_are_indexed_(false), features_are_mapped_(false),
is_error_(false) {
}
tesseract::TrainingSample::~TrainingSample ( )

Definition at line 45 of file trainingsample.cpp.

{
delete [] features_;
delete [] micro_features_;
}

Member Function Documentation

const TBOX& tesseract::TrainingSample::bounding_box ( ) const
inline

Definition at line 131 of file trainingsample.h.

{
return bounding_box_;
}
UNICHAR_ID tesseract::TrainingSample::class_id ( ) const
inline

Definition at line 113 of file trainingsample.h.

{
return class_id_;
}
float tesseract::TrainingSample::cn_feature ( int  index) const
inline

Definition at line 149 of file trainingsample.h.

{
return cn_feature_[index];
}
TrainingSample * tesseract::TrainingSample::Copy ( ) const

Definition at line 154 of file trainingsample.cpp.

{
sample->class_id_ = class_id_;
sample->font_id_ = font_id_;
sample->weight_ = weight_;
sample->sample_index_ = sample_index_;
sample->num_features_ = num_features_;
if (num_features_ > 0) {
sample->features_ = new INT_FEATURE_STRUCT[num_features_];
memcpy(sample->features_, features_, num_features_ * sizeof(features_[0]));
}
sample->num_micro_features_ = num_micro_features_;
if (num_micro_features_ > 0) {
sample->micro_features_ = new MicroFeature[num_micro_features_];
memcpy(sample->micro_features_, micro_features_,
num_micro_features_ * sizeof(micro_features_[0]));
}
memcpy(sample->cn_feature_, cn_feature_, sizeof(*cn_feature_) * kNumCNParams);
memcpy(sample->geo_feature_, geo_feature_, sizeof(*geo_feature_) * GeoCount);
return sample;
}
TrainingSample * tesseract::TrainingSample::CopyFromFeatures ( const INT_FX_RESULT_STRUCT fx_info,
const INT_FEATURE_STRUCT features,
int  num_features 
)
static

Definition at line 115 of file trainingsample.cpp.

{
sample->num_features_ = num_features;
sample->features_ = new INT_FEATURE_STRUCT[num_features];
memcpy(sample->features_, features, num_features * sizeof(features[0]));
sample->geo_feature_[GeoBottom] = fx_info.YBottom;
sample->geo_feature_[GeoTop] = fx_info.YTop;
sample->geo_feature_[GeoWidth] = fx_info.Width;
sample->features_are_indexed_ = false;
sample->features_are_mapped_ = false;
return sample;
}
bool tesseract::TrainingSample::DeSerialize ( bool  swap,
FILE *  fp 
)

Definition at line 85 of file trainingsample.cpp.

{
if (fread(&class_id_, sizeof(class_id_), 1, fp) != 1) return false;
if (fread(&font_id_, sizeof(font_id_), 1, fp) != 1) return false;
if (fread(&page_num_, sizeof(page_num_), 1, fp) != 1) return false;
if (!bounding_box_.DeSerialize(swap, fp)) return false;
if (fread(&num_features_, sizeof(num_features_), 1, fp) != 1) return false;
if (fread(&num_micro_features_, sizeof(num_micro_features_), 1, fp) != 1)
return false;
if (swap) {
ReverseN(&class_id_, sizeof(class_id_));
ReverseN(&num_features_, sizeof(num_features_));
ReverseN(&num_micro_features_, sizeof(num_micro_features_));
}
delete [] features_;
features_ = new INT_FEATURE_STRUCT[num_features_];
if (fread(features_, sizeof(*features_), num_features_, fp) != num_features_)
return false;
delete [] micro_features_;
micro_features_ = new MicroFeature[num_micro_features_];
if (fread(micro_features_, sizeof(*micro_features_), num_micro_features_,
fp) != num_micro_features_)
return false;
if (fread(cn_feature_, sizeof(*cn_feature_), kNumCNParams, fp) !=
kNumCNParams) return false;
if (fread(geo_feature_, sizeof(*geo_feature_), GeoCount, fp) != GeoCount)
return false;
return true;
}
TrainingSample * tesseract::TrainingSample::DeSerializeCreate ( bool  swap,
FILE *  fp 
)
static

Definition at line 76 of file trainingsample.cpp.

{
if (sample->DeSerialize(swap, fp)) return sample;
delete sample;
return NULL;
}
void tesseract::TrainingSample::DisplayFeatures ( ScrollView::Color  color,
ScrollView window 
) const

Definition at line 288 of file trainingsample.cpp.

{
#ifndef GRAPHICS_DISABLED
for (int f = 0; f < num_features_; ++f) {
RenderIntFeature(window, &features_[f], color);
}
#endif // GRAPHICS_DISABLED
}
void tesseract::TrainingSample::ExtractCharDesc ( int  feature_type,
int  micro_type,
int  cn_type,
int  geo_type,
CHAR_DESC_STRUCT char_desc 
)

Definition at line 177 of file trainingsample.cpp.

{
// Extract the INT features.
if (features_ != NULL) delete [] features_;
FEATURE_SET_STRUCT* char_features = char_desc->FeatureSets[int_feature_type];
if (char_features == NULL) {
tprintf("Error: no features to train on of type %s\n",
num_features_ = 0;
features_ = NULL;
} else {
num_features_ = char_features->NumFeatures;
features_ = new INT_FEATURE_STRUCT[num_features_];
for (int f = 0; f < num_features_; ++f) {
features_[f].X =
static_cast<uinT8>(char_features->Features[f]->Params[IntX]);
features_[f].Y =
static_cast<uinT8>(char_features->Features[f]->Params[IntY]);
features_[f].Theta =
static_cast<uinT8>(char_features->Features[f]->Params[IntDir]);
features_[f].CP_misses = 0;
}
}
// Extract the Micro features.
if (micro_features_ != NULL) delete [] micro_features_;
char_features = char_desc->FeatureSets[micro_type];
if (char_features == NULL) {
tprintf("Error: no features to train on of type %s\n",
num_micro_features_ = 0;
micro_features_ = NULL;
} else {
num_micro_features_ = char_features->NumFeatures;
micro_features_ = new MicroFeature[num_micro_features_];
for (int f = 0; f < num_micro_features_; ++f) {
for (int d = 0; d < MFCount; ++d) {
micro_features_[f][d] = char_features->Features[f]->Params[d];
}
}
}
// Extract the CN feature.
char_features = char_desc->FeatureSets[cn_type];
if (char_features == NULL) {
tprintf("Error: no CN feature to train on.\n");
} else {
ASSERT_HOST(char_features->NumFeatures == 1);
cn_feature_[CharNormY] = char_features->Features[0]->Params[CharNormY];
cn_feature_[CharNormLength] =
char_features->Features[0]->Params[CharNormLength];
cn_feature_[CharNormRx] = char_features->Features[0]->Params[CharNormRx];
cn_feature_[CharNormRy] = char_features->Features[0]->Params[CharNormRy];
}
// Extract the Geo feature.
char_features = char_desc->FeatureSets[geo_type];
if (char_features == NULL) {
tprintf("Error: no Geo feature to train on.\n");
} else {
ASSERT_HOST(char_features->NumFeatures == 1);
geo_feature_[GeoBottom] = char_features->Features[0]->Params[GeoBottom];
geo_feature_[GeoTop] = char_features->Features[0]->Params[GeoTop];
geo_feature_[GeoWidth] = char_features->Features[0]->Params[GeoWidth];
}
features_are_indexed_ = false;
features_are_mapped_ = false;
}
const INT_FEATURE_STRUCT* tesseract::TrainingSample::features ( ) const
inline

Definition at line 140 of file trainingsample.h.

{
return features_;
}
bool tesseract::TrainingSample::features_are_mapped ( ) const
inline

Definition at line 173 of file trainingsample.h.

{
return features_are_mapped_;
}
int tesseract::TrainingSample::font_id ( ) const
inline

Definition at line 119 of file trainingsample.h.

{
return font_id_;
}
int tesseract::TrainingSample::geo_feature ( int  index) const
inline

Definition at line 152 of file trainingsample.h.

{
return geo_feature_[index];
}
Pix * tesseract::TrainingSample::GetSamplePix ( int  padding,
Pix *  page_pix 
) const

Definition at line 301 of file trainingsample.cpp.

{
if (page_pix == NULL)
return NULL;
int page_width = pixGetWidth(page_pix);
int page_height = pixGetHeight(page_pix);
TBOX padded_box = bounding_box();
padded_box.pad(padding, padding);
// Clip the padded_box to the limits of the page
TBOX page_box(0, 0, page_width, page_height);
padded_box &= page_box;
Box* box = boxCreate(page_box.left(), page_height - page_box.top(),
page_box.width(), page_box.height());
Pix* sample_pix = pixClipRectangle(page_pix, box, NULL);
boxDestroy(&box);
return sample_pix;
}
const GenericVector<int>& tesseract::TrainingSample::indexed_features ( ) const
inline

Definition at line 180 of file trainingsample.h.

{
ASSERT_HOST(features_are_indexed_);
return mapped_features_;
}
void tesseract::TrainingSample::IndexFeatures ( const IntFeatureSpace feature_space)

Definition at line 248 of file trainingsample.cpp.

{
feature_space.IndexAndSortFeatures(features_, num_features_,
&mapped_features_);
features_are_indexed_ = true;
features_are_mapped_ = false;
}
bool tesseract::TrainingSample::is_error ( ) const
inline

Definition at line 184 of file trainingsample.h.

{
return is_error_;
}
void tesseract::TrainingSample::MapFeatures ( const IntFeatureMap feature_map)

Definition at line 258 of file trainingsample.cpp.

{
feature_map.feature_space().IndexAndSortFeatures(features_, num_features_,
&indexed_features);
feature_map.MapIndexedFeatures(indexed_features, &mapped_features_);
features_are_indexed_ = false;
features_are_mapped_ = true;
}
const GenericVector<int>& tesseract::TrainingSample::mapped_features ( ) const
inline

Definition at line 176 of file trainingsample.h.

{
ASSERT_HOST(features_are_mapped_);
return mapped_features_;
}
double tesseract::TrainingSample::max_dist ( ) const
inline

Definition at line 161 of file trainingsample.h.

{
return max_dist_;
}
const MicroFeature* tesseract::TrainingSample::micro_features ( ) const
inline

Definition at line 146 of file trainingsample.h.

{
return micro_features_;
}
int tesseract::TrainingSample::num_features ( ) const
inline

Definition at line 137 of file trainingsample.h.

{
return num_features_;
}
int tesseract::TrainingSample::num_micro_features ( ) const
inline

Definition at line 143 of file trainingsample.h.

{
return num_micro_features_;
}
int tesseract::TrainingSample::page_num ( ) const
inline

Definition at line 125 of file trainingsample.h.

{
return page_num_;
}
TrainingSample * tesseract::TrainingSample::RandomizedCopy ( int  index) const

Definition at line 133 of file trainingsample.cpp.

{
if (index >= 0 && index < kSampleRandomSize) {
++index; // Remove the first combination.
int yshift = kYShiftValues[index / kSampleScaleSize];
double scaling = kScaleValues[index % kSampleScaleSize];
for (int i = 0; i < num_features_; ++i) {
double result = (features_[i].X - kRandomizingCenter) * scaling;
result += kRandomizingCenter;
sample->features_[i].X = ClipToRange(static_cast<int>(result + 0.5), 0,
result = (features_[i].Y - kRandomizingCenter) * scaling;
result += kRandomizingCenter + yshift;
sample->features_[i].Y = ClipToRange(static_cast<int>(result + 0.5), 0,
}
}
return sample;
}
Pix * tesseract::TrainingSample::RenderToPix ( const UNICHARSET unicharset) const

Definition at line 268 of file trainingsample.cpp.

{
Pix* pix = pixCreate(kIntFeatureExtent, kIntFeatureExtent, 1);
for (int f = 0; f < num_features_; ++f) {
int start_x = features_[f].X;
int start_y = kIntFeatureExtent - features_[f].Y;
double dx = cos((features_[f].Theta / 256.0) * 2.0 * PI - PI);
double dy = -sin((features_[f].Theta / 256.0) * 2.0 * PI - PI);
for (int i = 0; i <= 5; ++i) {
int x = static_cast<int>(start_x + dx * i);
int y = static_cast<int>(start_y + dy * i);
if (x >= 0 && x < 256 && y >= 0 && y < 256)
pixSetPixel(pix, x, y, 1);
}
}
if (unicharset != NULL)
pixSetText(pix, unicharset->id_to_unichar(class_id_));
return pix;
}
int tesseract::TrainingSample::sample_index ( ) const
inline

Definition at line 167 of file trainingsample.h.

{
return sample_index_;
}
bool tesseract::TrainingSample::Serialize ( FILE *  fp) const

Definition at line 54 of file trainingsample.cpp.

{
if (fwrite(&class_id_, sizeof(class_id_), 1, fp) != 1) return false;
if (fwrite(&font_id_, sizeof(font_id_), 1, fp) != 1) return false;
if (fwrite(&page_num_, sizeof(page_num_), 1, fp) != 1) return false;
if (!bounding_box_.Serialize(fp)) return false;
if (fwrite(&num_features_, sizeof(num_features_), 1, fp) != 1) return false;
if (fwrite(&num_micro_features_, sizeof(num_micro_features_), 1, fp) != 1)
return false;
if (fwrite(features_, sizeof(*features_), num_features_, fp) != num_features_)
return false;
if (fwrite(micro_features_, sizeof(*micro_features_), num_micro_features_,
fp) != num_micro_features_)
return false;
if (fwrite(cn_feature_, sizeof(*cn_feature_), kNumCNParams, fp) !=
kNumCNParams) return false;
if (fwrite(geo_feature_, sizeof(*geo_feature_), GeoCount, fp) != GeoCount)
return false;
return true;
}
void tesseract::TrainingSample::set_bounding_box ( const TBOX box)
inline

Definition at line 134 of file trainingsample.h.

{
bounding_box_ = box;
}
void tesseract::TrainingSample::set_class_id ( int  id)
inline

Definition at line 116 of file trainingsample.h.

{
class_id_ = id;
}
void tesseract::TrainingSample::set_font_id ( int  id)
inline

Definition at line 122 of file trainingsample.h.

{
font_id_ = id;
}
void tesseract::TrainingSample::set_is_error ( bool  value)
inline

Definition at line 187 of file trainingsample.h.

{
is_error_ = value;
}
void tesseract::TrainingSample::set_max_dist ( double  value)
inline

Definition at line 164 of file trainingsample.h.

{
max_dist_ = value;
}
void tesseract::TrainingSample::set_page_num ( int  page)
inline

Definition at line 128 of file trainingsample.h.

{
page_num_ = page;
}
void tesseract::TrainingSample::set_sample_index ( int  value)
inline

Definition at line 170 of file trainingsample.h.

{
sample_index_ = value;
}
void tesseract::TrainingSample::set_weight ( double  value)
inline

Definition at line 158 of file trainingsample.h.

{
weight_ = value;
}
double tesseract::TrainingSample::weight ( ) const
inline

Definition at line 155 of file trainingsample.h.

{
return weight_;
}

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