// Returns the mean confidence of the current object at the given level.
// The number should be interpreted as a percent probability. (0.0f-100.0f)
float LTRResultIterator::Confidence(PageIteratorLevel level) const {
if (it_->word() == NULL) return 0.0f; // Already at the end!
float mean_certainty = 0.0f;
int certainty_count = 0;
PAGE_RES_IT res_it(*it_);
WERD_CHOICE* best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
switch (level) {
case RIL_BLOCK:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.block() == res_it.prev_block());
break;
case RIL_PARA:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.block() == res_it.prev_block() &&
res_it.row()->row->para() == res_it.prev_row()->row->para());
break;
case RIL_TEXTLINE:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.row() == res_it.prev_row());
break;
case RIL_WORD:
mean_certainty += best_choice->certainty();
++certainty_count;
break;
case RIL_SYMBOL:
mean_certainty += best_choice->certainty(blob_index_);
++certainty_count;
}
if (certainty_count > 0) {
mean_certainty /= certainty_count;
float confidence = 100 + 5 * mean_certainty;
if (confidence < 0.0f) confidence = 0.0f;
if (confidence > 100.0f) confidence = 100.0f;
return confidence;
}
return 0.0f;
}
ChoiceIterator::ChoiceIterator(const LTRResultIterator& result_it) {
ASSERT_HOST(result_it.it_->word() != NULL);
word_res_ = result_it.it_->word();
PAGE_RES_IT res_it(*result_it.it_);
WERD_CHOICE* best_choice = word_res_->best_choice;
BLOB_CHOICE_LIST_CLIST* choices = best_choice->blob_choices();
if (choices != NULL) {
BLOB_CHOICE_LIST_C_IT blob_choices_it(choices);
for (int blob = 0; blob < result_it.blob_index_; ++blob)
blob_choices_it.forward();
choice_it_ = new BLOB_CHOICE_IT(blob_choices_it.data());
choice_it_->mark_cycle_pt();
} else {
choice_it_ = NULL;
}
}
bool Residue::isCTerminal() const
{
if (isAminoAcid() == true)
{
const Chain* chain = getChain();
if (chain != 0)
{
ResidueConstIterator res_it(chain->endResidue());
for (--res_it; +res_it && &(*res_it) != this && !res_it->isAminoAcid(); --res_it) {};
return (&(*res_it) == this);
}
}
return false;
}
// Returns an array of all word confidences, terminated by -1.
int* TessBaseAPI::AllTextConfidences(PAGE_RES* page_res) {
if (!page_res) return NULL;
int n_word = 0;
PAGE_RES_IT res_it(page_res);
for (res_it.restart_page(); res_it.word () != NULL; res_it.forward())
n_word++;
int* conf = new int[n_word+1];
n_word = 0;
for (res_it.restart_page(); res_it.word () != NULL; res_it.forward()) {
WERD_RES *word = res_it.word();
WERD_CHOICE* choice = word->best_choice;
int w_conf = static_cast<int>(100 + 5 * choice->certainty());
// This is the eq for converting Tesseract confidence to 1..100
if (w_conf < 0) w_conf = 0;
if (w_conf > 100) w_conf = 100;
conf[n_word++] = w_conf;
}
conf[n_word] = -1;
return conf;
}
// Returns the null terminated UTF-8 encoded text string for the current
// object at the given level. Use delete [] to free after use.
char* LTRResultIterator::GetUTF8Text(PageIteratorLevel level) const {
if (it_->word() == NULL) return NULL; // Already at the end!
STRING text;
PAGE_RES_IT res_it(*it_);
WERD_CHOICE* best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
if (level == RIL_SYMBOL) {
text = res_it.word()->BestUTF8(blob_index_, false);
} else if (level == RIL_WORD) {
text = best_choice->unichar_string();
} else {
bool eol = false; // end of line?
bool eop = false; // end of paragraph?
do { // for each paragraph in a block
do { // for each text line in a paragraph
do { // for each word in a text line
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
text += best_choice->unichar_string();
text += " ";
res_it.forward();
eol = res_it.row() != res_it.prev_row();
} while (!eol);
text.truncate_at(text.length() - 1);
text += line_separator_;
eop = res_it.block() != res_it.prev_block() ||
res_it.row()->row->para() != res_it.prev_row()->row->para();
} while (level != RIL_TEXTLINE && !eop);
if (eop) text += paragraph_separator_;
} while (level == RIL_BLOCK && res_it.block() == res_it.prev_block());
}
int length = text.length() + 1;
char* result = new char[length];
strncpy(result, text.string(), length);
return result;
}
// Returns the mean confidence of the current object at the given level.
// The number should be interpreted as a percent probability. (0.0f-100.0f)
float LTRResultIterator::Confidence(PageIteratorLevel level) const {
if (it_->word() == NULL) return 0.0f; // Already at the end!
float mean_certainty = 0.0f;
int certainty_count = 0;
PAGE_RES_IT res_it(*it_);
WERD_CHOICE* best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
switch (level) {
case RIL_BLOCK:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.block() == res_it.prev_block());
break;
case RIL_PARA:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.block() == res_it.prev_block() &&
res_it.row()->row->para() == res_it.prev_row()->row->para());
break;
case RIL_TEXTLINE:
do {
best_choice = res_it.word()->best_choice;
ASSERT_HOST(best_choice != NULL);
mean_certainty += best_choice->certainty();
++certainty_count;
res_it.forward();
} while (res_it.row() == res_it.prev_row());
break;
case RIL_WORD:
mean_certainty += best_choice->certainty();
++certainty_count;
break;
case RIL_SYMBOL:
BLOB_CHOICE_LIST_CLIST* choices = best_choice->blob_choices();
if (choices != NULL) {
BLOB_CHOICE_LIST_C_IT blob_choices_it(choices);
for (int blob = 0; blob < blob_index_; ++blob)
blob_choices_it.forward();
BLOB_CHOICE_IT choice_it(blob_choices_it.data());
for (choice_it.mark_cycle_pt();
!choice_it.cycled_list();
choice_it.forward()) {
if (choice_it.data()->unichar_id() ==
best_choice->unichar_id(blob_index_))
break;
}
mean_certainty += choice_it.data()->certainty();
} else {
mean_certainty += best_choice->certainty();
}
++certainty_count;
}
if (certainty_count > 0) {
mean_certainty /= certainty_count;
float confidence = 100 + 5 * mean_certainty;
if (confidence < 0.0f) confidence = 0.0f;
if (confidence > 100.0f) confidence = 100.0f;
return confidence;
}
return 0.0f;
}