/**
* @name classify_blob
*
* Classify the this blob if it is not already recorded in the match
* table. Attempt to recognize this blob as a character. The recognition
* rating for this blob will be stored as a part of the blob. This value
* will also be returned to the caller.
* @param blob Current blob
* @param string The string to display in ScrollView
* @param color The colour to use when displayed with ScrollView
*/
BLOB_CHOICE_LIST *Wordrec::classify_blob(TBLOB *blob,
const char *string, C_COL color,
BlamerBundle *blamer_bundle) {
#ifndef GRAPHICS_DISABLED
if (wordrec_display_all_blobs)
display_blob(blob, color);
#endif
// TODO(rays) collapse with call_matcher and move all to wordrec.cpp.
BLOB_CHOICE_LIST* choices = call_matcher(blob);
// If a blob with the same bounding box as one of the truth character
// bounding boxes is not classified as the corresponding truth character
// blame character classifier for incorrect answer.
if (blamer_bundle != NULL) {
blamer_bundle->BlameClassifier(getDict().getUnicharset(),
blob->bounding_box(),
*choices,
wordrec_debug_blamer);
}
#ifndef GRAPHICS_DISABLED
if (classify_debug_level && string)
print_ratings_list(string, choices, getDict().getUnicharset());
if (wordrec_blob_pause)
window_wait(blob_window);
#endif
return choices;
}
void Wordrec::ProcessSegSearchPainPoint(
float pain_point_priority,
const MATRIX_COORD &pain_point, const char* pain_point_type,
GenericVector<SegSearchPending>* pending, WERD_RES *word_res,
LMPainPoints *pain_points, BlamerBundle *blamer_bundle) {
if (segsearch_debug_level > 0) {
tprintf("Classifying pain point %s priority=%.4f, col=%d, row=%d\n",
pain_point_type, pain_point_priority,
pain_point.col, pain_point.row);
}
ASSERT_HOST(pain_points != NULL);
MATRIX *ratings = word_res->ratings;
// Classify blob [pain_point.col pain_point.row]
if (!pain_point.Valid(*ratings)) {
ratings->IncreaseBandSize(pain_point.row + 1 - pain_point.col);
}
ASSERT_HOST(pain_point.Valid(*ratings));
BLOB_CHOICE_LIST *classified = classify_piece(word_res->seam_array,
pain_point.col, pain_point.row,
pain_point_type,
word_res->chopped_word,
blamer_bundle);
BLOB_CHOICE_LIST *lst = ratings->get(pain_point.col, pain_point.row);
if (lst == NULL) {
ratings->put(pain_point.col, pain_point.row, classified);
} else {
// We can not delete old BLOB_CHOICEs, since they might contain
// ViterbiStateEntries that are parents of other "active" entries.
// Thus if the matrix cell already contains classifications we add
// the new ones to the beginning of the list.
BLOB_CHOICE_IT it(lst);
it.add_list_before(classified);
delete classified; // safe to delete, since empty after add_list_before()
classified = NULL;
}
if (segsearch_debug_level > 0) {
print_ratings_list("Updated ratings matrix with a new entry:",
ratings->get(pain_point.col, pain_point.row),
getDict().getUnicharset());
ratings->print(getDict().getUnicharset());
}
// Insert initial "pain points" to join the newly classified blob
// with its left and right neighbors.
if (classified != NULL && !classified->empty()) {
if (pain_point.col > 0) {
pain_points->GeneratePainPoint(
pain_point.col - 1, pain_point.row, LM_PPTYPE_SHAPE, 0.0,
true, segsearch_max_char_wh_ratio, word_res);
}
if (pain_point.row + 1 < ratings->dimension()) {
pain_points->GeneratePainPoint(
pain_point.col, pain_point.row + 1, LM_PPTYPE_SHAPE, 0.0,
true, segsearch_max_char_wh_ratio, word_res);
}
}
(*pending)[pain_point.col].SetBlobClassified(pain_point.row);
}
/// Resegments the word to achieve the target_text from the classifier.
/// Returns false if the re-segmentation fails.
/// Uses brute-force combination of up to #kMaxGroupSize adjacent blobs, and
/// applies a full search on the classifier results to find the best classified
/// segmentation. As a compromise to obtain better recall, 1-1 ambiguity
/// substitutions ARE used.
bool Tesseract::FindSegmentation(const GenericVector<UNICHAR_ID>& target_text,
WERD_RES* word_res) {
// Classify all required combinations of blobs and save results in choices.
int word_length = word_res->box_word->length();
GenericVector<BLOB_CHOICE_LIST*>* choices =
new GenericVector<BLOB_CHOICE_LIST*>[word_length];
for (int i = 0; i < word_length; ++i) {
for (int j = 1; j <= kMaxGroupSize && i + j <= word_length; ++j) {
BLOB_CHOICE_LIST* match_result = classify_piece(
word_res->seam_array, i, i + j - 1, "Applybox",
word_res->chopped_word, word_res->blamer_bundle);
if (applybox_debug > 2) {
tprintf("%d+%d:", i, j);
print_ratings_list("Segment:", match_result, unicharset);
}
choices[i].push_back(match_result);
}
}
// Search the segmentation graph for the target text. Must be an exact
// match. Using wildcards makes it difficult to find the correct
// segmentation even when it is there.
word_res->best_state.clear();
GenericVector<int> search_segmentation;
float best_rating = 0.0f;
SearchForText(choices, 0, word_length, target_text, 0, 0.0f,
&search_segmentation, &best_rating, &word_res->best_state);
for (int i = 0; i < word_length; ++i)
choices[i].delete_data_pointers();
delete [] choices;
if (word_res->best_state.empty()) {
// Build the original segmentation and if it is the same length as the
// truth, assume it will do.
int blob_count = 1;
for (int s = 0; s < word_res->seam_array.size(); ++s) {
SEAM* seam = word_res->seam_array[s];
if (!seam->HasAnySplits()) {
word_res->best_state.push_back(blob_count);
blob_count = 1;
} else {
++blob_count;
}
}
word_res->best_state.push_back(blob_count);
if (word_res->best_state.size() != target_text.size()) {
word_res->best_state.clear(); // No good. Original segmentation bad size.
return false;
}
}
word_res->correct_text.clear();
for (int i = 0; i < target_text.size(); ++i) {
word_res->correct_text.push_back(
STRING(unicharset.id_to_unichar(target_text[i])));
}
return true;
}
/**
* print_char_choices_list
*/
void print_char_choices_list(const char *msg,
const BLOB_CHOICE_LIST_VECTOR &char_choices,
const UNICHARSET ¤t_unicharset,
BOOL8 detailed) {
if (*msg != '\0') tprintf("%s\n", msg);
for (int x = 0; x < char_choices.length(); ++x) {
BLOB_CHOICE_IT c_it;
c_it.set_to_list(char_choices.get(x));
tprintf("char[%d]: %s\n", x,
current_unicharset.debug_str( c_it.data()->unichar_id()).string());
if (detailed)
print_ratings_list(" ", char_choices.get(x), current_unicharset);
}
}
// Creates a fake blob choice from the combination of the given fragments.
// unichar is the class to be made from the combination,
// expanded_fragment_lengths[choice_index] is the number of fragments to use.
// old_choices[choice_index] has the classifier output for each fragment.
// choice index initially indexes the last fragment and should be decremented
// expanded_fragment_lengths[choice_index] times to get the earlier fragments.
// Guarantees to return something non-null, or abort!
BLOB_CHOICE* Wordrec::rebuild_fragments(
const char* unichar,
const char* expanded_fragment_lengths,
int choice_index,
BLOB_CHOICE_LIST_VECTOR *old_choices) {
float rating = 0.0f;
float certainty = 0.0f;
inT16 min_xheight = -MAX_INT16;
inT16 max_xheight = MAX_INT16;
for (int fragment_pieces = expanded_fragment_lengths[choice_index] - 1;
fragment_pieces >= 0; --fragment_pieces, --choice_index) {
// Get a pointer to the classifier results from the old_choices.
BLOB_CHOICE_LIST *current_choices = old_choices->get(choice_index);
// Populate fragment with updated values and look for the
// fragment with the same values in current_choices.
// Update rating and certainty of the character being composed.
CHAR_FRAGMENT fragment;
fragment.set_all(unichar, fragment_pieces,
expanded_fragment_lengths[choice_index], false);
BLOB_CHOICE_IT choice_it(current_choices);
for (choice_it.mark_cycle_pt(); !choice_it.cycled_list();
choice_it.forward()) {
BLOB_CHOICE* choice = choice_it.data();
const CHAR_FRAGMENT *current_fragment =
getDict().getUnicharset().get_fragment(choice->unichar_id());
if (current_fragment && fragment.equals(current_fragment)) {
rating += choice->rating();
if (choice->certainty() < certainty) {
certainty = choice->certainty();
}
IntersectRange(choice->min_xheight(), choice->max_xheight(),
&min_xheight, &max_xheight);
break;
}
}
if (choice_it.cycled_list()) {
print_ratings_list("Failure", current_choices, unicharset);
tprintf("Failed to find fragment %s at index=%d\n",
fragment.to_string().string(), choice_index);
}
ASSERT_HOST(!choice_it.cycled_list()); // Be sure we found the fragment.
}
return new BLOB_CHOICE(getDict().getUnicharset().unichar_to_id(unichar),
rating, certainty, -1, -1, 0,
min_xheight, max_xheight, false);
}
void Dict::ReplaceAmbig(int wrong_ngram_begin_index, int wrong_ngram_size,
UNICHAR_ID correct_ngram_id, WERD_CHOICE *werd_choice,
MATRIX *ratings) {
int num_blobs_to_replace = 0;
int begin_blob_index = 0;
int i;
// Rating and certainty for the new BLOB_CHOICE are derived from the
// replaced choices.
float new_rating = 0.0f;
float new_certainty = 0.0f;
BLOB_CHOICE* old_choice = nullptr;
for (i = 0; i < wrong_ngram_begin_index + wrong_ngram_size; ++i) {
if (i >= wrong_ngram_begin_index) {
int num_blobs = werd_choice->state(i);
int col = begin_blob_index + num_blobs_to_replace;
int row = col + num_blobs - 1;
BLOB_CHOICE_LIST* choices = ratings->get(col, row);
ASSERT_HOST(choices != nullptr);
old_choice = FindMatchingChoice(werd_choice->unichar_id(i), choices);
ASSERT_HOST(old_choice != nullptr);
new_rating += old_choice->rating();
new_certainty += old_choice->certainty();
num_blobs_to_replace += num_blobs;
} else {
begin_blob_index += werd_choice->state(i);
}
}
new_certainty /= wrong_ngram_size;
// If there is no entry in the ratings matrix, add it.
MATRIX_COORD coord(begin_blob_index,
begin_blob_index + num_blobs_to_replace - 1);
if (!coord.Valid(*ratings)) {
ratings->IncreaseBandSize(coord.row - coord.col + 1);
}
if (ratings->get(coord.col, coord.row) == nullptr)
ratings->put(coord.col, coord.row, new BLOB_CHOICE_LIST);
BLOB_CHOICE_LIST* new_choices = ratings->get(coord.col, coord.row);
BLOB_CHOICE* choice = FindMatchingChoice(correct_ngram_id, new_choices);
if (choice != nullptr) {
// Already there. Upgrade if new rating better.
if (new_rating < choice->rating())
choice->set_rating(new_rating);
if (new_certainty < choice->certainty())
choice->set_certainty(new_certainty);
// DO NOT SORT!! It will mess up the iterator in LanguageModel::UpdateState.
} else {
// Need a new choice with the correct_ngram_id.
choice = new BLOB_CHOICE(*old_choice);
choice->set_unichar_id(correct_ngram_id);
choice->set_rating(new_rating);
choice->set_certainty(new_certainty);
choice->set_classifier(BCC_AMBIG);
choice->set_matrix_cell(coord.col, coord.row);
BLOB_CHOICE_IT it (new_choices);
it.add_to_end(choice);
}
// Remove current unichar from werd_choice. On the last iteration
// set the correct replacement unichar instead of removing a unichar.
for (int replaced_count = 0; replaced_count < wrong_ngram_size;
++replaced_count) {
if (replaced_count + 1 == wrong_ngram_size) {
werd_choice->set_blob_choice(wrong_ngram_begin_index,
num_blobs_to_replace, choice);
} else {
werd_choice->remove_unichar_id(wrong_ngram_begin_index + 1);
}
}
if (stopper_debug_level >= 1) {
werd_choice->print("ReplaceAmbig() ");
tprintf("Modified blob_choices: ");
print_ratings_list("\n", new_choices, getUnicharset());
}
}
bool Dict::NoDangerousAmbig(WERD_CHOICE *best_choice,
DANGERR *fixpt,
bool fix_replaceable,
MATRIX *ratings) {
if (stopper_debug_level > 2) {
tprintf("\nRunning NoDangerousAmbig() for %s\n",
best_choice->debug_string().string());
}
// Construct BLOB_CHOICE_LIST_VECTOR with ambiguities
// for each unichar id in BestChoice.
BLOB_CHOICE_LIST_VECTOR ambig_blob_choices;
int i;
bool ambigs_found = false;
// For each position in best_choice:
// -- choose AMBIG_SPEC_LIST that corresponds to unichar_id at best_choice[i]
// -- initialize wrong_ngram with a single unichar_id at best_choice[i]
// -- look for ambiguities corresponding to wrong_ngram in the list while
// adding the following unichar_ids from best_choice to wrong_ngram
//
// Repeat the above procedure twice: first time look through
// ambigs to be replaced and replace all the ambiguities found;
// second time look through dangerous ambiguities and construct
// ambig_blob_choices with fake a blob choice for each ambiguity
// and pass them to dawg_permute_and_select() to search for
// ambiguous words in the dictionaries.
//
// Note that during the execution of the for loop (on the first pass)
// if replacements are made the length of best_choice might change.
for (int pass = 0; pass < (fix_replaceable ? 2 : 1); ++pass) {
bool replace = (fix_replaceable && pass == 0);
const UnicharAmbigsVector &table = replace ?
getUnicharAmbigs().replace_ambigs() : getUnicharAmbigs().dang_ambigs();
if (!replace) {
// Initialize ambig_blob_choices with lists containing a single
// unichar id for the correspoding position in best_choice.
// best_choice consisting from only the original letters will
// have a rating of 0.0.
for (i = 0; i < best_choice->length(); ++i) {
BLOB_CHOICE_LIST *lst = new BLOB_CHOICE_LIST();
BLOB_CHOICE_IT lst_it(lst);
// TODO(rays/antonova) Put real xheights and y shifts here.
lst_it.add_to_end(new BLOB_CHOICE(best_choice->unichar_id(i),
0.0, 0.0, -1, 0, 1, 0, BCC_AMBIG));
ambig_blob_choices.push_back(lst);
}
}
UNICHAR_ID wrong_ngram[MAX_AMBIG_SIZE + 1];
int wrong_ngram_index;
int next_index;
int blob_index = 0;
for (i = 0; i < best_choice->length(); blob_index += best_choice->state(i),
++i) {
UNICHAR_ID curr_unichar_id = best_choice->unichar_id(i);
if (stopper_debug_level > 2) {
tprintf("Looking for %s ngrams starting with %s:\n",
replace ? "replaceable" : "ambiguous",
getUnicharset().debug_str(curr_unichar_id).string());
}
int num_wrong_blobs = best_choice->state(i);
wrong_ngram_index = 0;
wrong_ngram[wrong_ngram_index] = curr_unichar_id;
if (curr_unichar_id == INVALID_UNICHAR_ID ||
curr_unichar_id >= table.size() ||
table[curr_unichar_id] == nullptr) {
continue; // there is no ambig spec for this unichar id
}
AmbigSpec_IT spec_it(table[curr_unichar_id]);
for (spec_it.mark_cycle_pt(); !spec_it.cycled_list();) {
const AmbigSpec *ambig_spec = spec_it.data();
wrong_ngram[wrong_ngram_index+1] = INVALID_UNICHAR_ID;
int compare = UnicharIdArrayUtils::compare(wrong_ngram,
ambig_spec->wrong_ngram);
if (stopper_debug_level > 2) {
tprintf("candidate ngram: ");
UnicharIdArrayUtils::print(wrong_ngram, getUnicharset());
tprintf("current ngram from spec: ");
UnicharIdArrayUtils::print(ambig_spec->wrong_ngram, getUnicharset());
tprintf("comparison result: %d\n", compare);
}
if (compare == 0) {
// Record the place where we found an ambiguity.
if (fixpt != nullptr) {
UNICHAR_ID leftmost_id = ambig_spec->correct_fragments[0];
fixpt->push_back(DANGERR_INFO(
blob_index, blob_index + num_wrong_blobs, replace,
getUnicharset().get_isngram(ambig_spec->correct_ngram_id),
leftmost_id));
if (stopper_debug_level > 1) {
tprintf("fixpt+=(%d %d %d %d %s)\n", blob_index,
blob_index + num_wrong_blobs, false,
getUnicharset().get_isngram(
ambig_spec->correct_ngram_id),
getUnicharset().id_to_unichar(leftmost_id));
}
}
if (replace) {
if (stopper_debug_level > 2) {
tprintf("replace ambiguity with %s : ",
getUnicharset().id_to_unichar(
ambig_spec->correct_ngram_id));
UnicharIdArrayUtils::print(
ambig_spec->correct_fragments, getUnicharset());
}
ReplaceAmbig(i, ambig_spec->wrong_ngram_size,
ambig_spec->correct_ngram_id,
best_choice, ratings);
} else if (i > 0 || ambig_spec->type != CASE_AMBIG) {
// We found dang ambig - update ambig_blob_choices.
if (stopper_debug_level > 2) {
tprintf("found ambiguity: ");
UnicharIdArrayUtils::print(
ambig_spec->correct_fragments, getUnicharset());
}
ambigs_found = true;
for (int tmp_index = 0; tmp_index <= wrong_ngram_index;
++tmp_index) {
// Add a blob choice for the corresponding fragment of the
// ambiguity. These fake blob choices are initialized with
// negative ratings (which are not possible for real blob
// choices), so that dawg_permute_and_select() considers any
// word not consisting of only the original letters a better
// choice and stops searching for alternatives once such a
// choice is found.
BLOB_CHOICE_IT bc_it(ambig_blob_choices[i+tmp_index]);
bc_it.add_to_end(new BLOB_CHOICE(
ambig_spec->correct_fragments[tmp_index], -1.0, 0.0,
-1, 0, 1, 0, BCC_AMBIG));
}
}
spec_it.forward();
} else if (compare == -1) {
if (wrong_ngram_index+1 < ambig_spec->wrong_ngram_size &&
((next_index = wrong_ngram_index+1+i) < best_choice->length())) {
// Add the next unichar id to wrong_ngram and keep looking for
// more ambigs starting with curr_unichar_id in AMBIG_SPEC_LIST.
wrong_ngram[++wrong_ngram_index] =
best_choice->unichar_id(next_index);
num_wrong_blobs += best_choice->state(next_index);
} else {
break; // no more matching ambigs in this AMBIG_SPEC_LIST
}
} else {
spec_it.forward();
}
} // end searching AmbigSpec_LIST
} // end searching best_choice
} // end searching replace and dangerous ambigs
// If any ambiguities were found permute the constructed ambig_blob_choices
// to see if an alternative dictionary word can be found.
if (ambigs_found) {
if (stopper_debug_level > 2) {
tprintf("\nResulting ambig_blob_choices:\n");
for (i = 0; i < ambig_blob_choices.length(); ++i) {
print_ratings_list("", ambig_blob_choices.get(i), getUnicharset());
tprintf("\n");
}
}
WERD_CHOICE *alt_word = dawg_permute_and_select(ambig_blob_choices, 0.0);
ambigs_found = (alt_word->rating() < 0.0);
if (ambigs_found) {
if (stopper_debug_level >= 1) {
tprintf ("Stopper: Possible ambiguous word = %s\n",
alt_word->debug_string().string());
}
if (fixpt != nullptr) {
// Note: Currently character choices combined from fragments can only
// be generated by NoDangrousAmbigs(). This code should be updated if
// the capability to produce classifications combined from character
// fragments is added to other functions.
int orig_i = 0;
for (i = 0; i < alt_word->length(); ++i) {
const UNICHARSET &uchset = getUnicharset();
bool replacement_is_ngram =
uchset.get_isngram(alt_word->unichar_id(i));
UNICHAR_ID leftmost_id = alt_word->unichar_id(i);
if (replacement_is_ngram) {
// we have to extract the leftmost unichar from the ngram.
const char *str = uchset.id_to_unichar(leftmost_id);
int step = uchset.step(str);
if (step) leftmost_id = uchset.unichar_to_id(str, step);
}
int end_i = orig_i + alt_word->state(i);
if (alt_word->state(i) > 1 ||
(orig_i + 1 == end_i && replacement_is_ngram)) {
// Compute proper blob indices.
int blob_start = 0;
for (int j = 0; j < orig_i; ++j)
blob_start += best_choice->state(j);
int blob_end = blob_start;
for (int j = orig_i; j < end_i; ++j)
blob_end += best_choice->state(j);
fixpt->push_back(DANGERR_INFO(blob_start, blob_end, true,
replacement_is_ngram, leftmost_id));
if (stopper_debug_level > 1) {
tprintf("fixpt->dangerous+=(%d %d %d %d %s)\n", orig_i, end_i,
true, replacement_is_ngram,
uchset.id_to_unichar(leftmost_id));
}
}
orig_i += alt_word->state(i);
}
}
}
delete alt_word;
}
if (output_ambig_words_file_ != nullptr) {
fprintf(output_ambig_words_file_, "\n");
}
ambig_blob_choices.delete_data_pointers();
return !ambigs_found;
}
void Wordrec::SegSearch(CHUNKS_RECORD *chunks_record,
WERD_CHOICE *best_choice,
BLOB_CHOICE_LIST_VECTOR *best_char_choices,
WERD_CHOICE *raw_choice,
STATE *output_best_state) {
int row, col = 0;
if (segsearch_debug_level > 0) {
tprintf("Starting SegSearch on ratings matrix:\n");
chunks_record->ratings->print(getDict().getUnicharset());
}
// Start with a fresh best_choice since rating adjustments
// used by the chopper and the new segmentation search are not compatible.
best_choice->set_rating(WERD_CHOICE::kBadRating);
// Clear best choice accumulator (that is used for adaption), so that
// choices adjusted by chopper do not interfere with the results from the
// segmentation search.
getDict().ClearBestChoiceAccum();
MATRIX *ratings = chunks_record->ratings;
// Priority queue containing pain points generated by the language model
// The priority is set by the language model components, adjustments like
// seam cost and width priority are factored into the priority.
HEAP *pain_points = MakeHeap(segsearch_max_pain_points);
// best_path_by_column records the lowest cost path found so far for each
// column of the chunks_record->ratings matrix over all the rows.
BestPathByColumn *best_path_by_column =
new BestPathByColumn[ratings->dimension()];
for (col = 0; col < ratings->dimension(); ++col) {
best_path_by_column[col].avg_cost = WERD_CHOICE::kBadRating;
best_path_by_column[col].best_vse = NULL;
}
language_model_->InitForWord(prev_word_best_choice_, &denorm_,
assume_fixed_pitch_char_segment,
best_choice->certainty(),
segsearch_max_char_wh_ratio,
pain_points, chunks_record);
MATRIX_COORD *pain_point;
float pain_point_priority;
BestChoiceBundle best_choice_bundle(
output_best_state, best_choice, raw_choice, best_char_choices);
// pending[i] stores a list of the parent/child pair of BLOB_CHOICE_LISTs,
// where i is the column of the child. Initially all the classified entries
// in the ratings matrix from column 0 (with parent NULL) are inserted into
// pending[0]. As the language model state is updated, new child/parent
// pairs are inserted into the lists. Next, the entries in pending[1] are
// considered, and so on. It is important that during the update the
// children are considered in the non-decreasing order of their column, since
// this guarantess that all the parents would be up to date before an update
// of a child is done.
SEG_SEARCH_PENDING_LIST *pending =
new SEG_SEARCH_PENDING_LIST[ratings->dimension()];
// Search for the ratings matrix for the initial best path.
for (row = 0; row < ratings->dimension(); ++row) {
if (ratings->get(0, row) != NOT_CLASSIFIED) {
pending[0].add_sorted(
SEG_SEARCH_PENDING::compare, true,
new SEG_SEARCH_PENDING(row, NULL, LanguageModel::kAllChangedFlag));
}
}
UpdateSegSearchNodes(0, &pending, &best_path_by_column, chunks_record,
pain_points, &best_choice_bundle);
// Keep trying to find a better path by fixing the "pain points".
int num_futile_classifications = 0;
while (!(language_model_->AcceptableChoiceFound() ||
num_futile_classifications >=
segsearch_max_futile_classifications)) {
// Get the next valid "pain point".
int pop;
while (true) {
pop = HeapPop(pain_points, &pain_point_priority, &pain_point);
if (pop == EMPTY) break;
if (pain_point->Valid(*ratings) &&
ratings->get(pain_point->col, pain_point->row) == NOT_CLASSIFIED) {
break;
} else {
delete pain_point;
}
}
if (pop == EMPTY) {
if (segsearch_debug_level > 0) tprintf("Pain points queue is empty\n");
break;
}
if (segsearch_debug_level > 0) {
tprintf("Classifying pain point priority=%.4f, col=%d, row=%d\n",
pain_point_priority, pain_point->col, pain_point->row);
}
BLOB_CHOICE_LIST *classified = classify_piece(
chunks_record->chunks, chunks_record->splits,
pain_point->col, pain_point->row);
ratings->put(pain_point->col, pain_point->row, classified);
if (segsearch_debug_level > 0) {
print_ratings_list("Updated ratings matrix with a new entry:",
ratings->get(pain_point->col, pain_point->row),
getDict().getUnicharset());
chunks_record->ratings->print(getDict().getUnicharset());
}
// Insert initial "pain points" to join the newly classified blob
// with its left and right neighbors.
if (!classified->empty()) {
float worst_piece_cert;
bool fragmented;
if (pain_point->col > 0) {
language_model_->GetWorstPieceCertainty(
pain_point->col-1, pain_point->row, chunks_record->ratings,
&worst_piece_cert, &fragmented);
language_model_->GeneratePainPoint(
pain_point->col-1, pain_point->row, false,
LanguageModel::kInitialPainPointPriorityAdjustment,
worst_piece_cert, fragmented, best_choice->certainty(),
segsearch_max_char_wh_ratio, NULL, NULL,
chunks_record, pain_points);
}
if (pain_point->row+1 < ratings->dimension()) {
language_model_->GetWorstPieceCertainty(
pain_point->col, pain_point->row+1, chunks_record->ratings,
&worst_piece_cert, &fragmented);
language_model_->GeneratePainPoint(
pain_point->col, pain_point->row+1, true,
LanguageModel::kInitialPainPointPriorityAdjustment,
worst_piece_cert, fragmented, best_choice->certainty(),
segsearch_max_char_wh_ratio, NULL, NULL,
chunks_record, pain_points);
}
}
// Record a pending entry with the pain_point and each of its parents.
int parent_row = pain_point->col - 1;
if (parent_row < 0) { // this node has no parents
pending[pain_point->col].add_sorted(
SEG_SEARCH_PENDING::compare, true,
new SEG_SEARCH_PENDING(pain_point->row, NULL,
LanguageModel::kAllChangedFlag));
} else {
for (int parent_col = 0; parent_col < pain_point->col; ++parent_col) {
if (ratings->get(parent_col, parent_row) != NOT_CLASSIFIED) {
pending[pain_point->col].add_sorted(
SEG_SEARCH_PENDING::compare, true,
new SEG_SEARCH_PENDING(pain_point->row,
ratings->get(parent_col, parent_row),
LanguageModel::kAllChangedFlag));
}
}
}
UpdateSegSearchNodes(pain_point->col, &pending, &best_path_by_column,
chunks_record, pain_points, &best_choice_bundle);
if (!best_choice_bundle.updated) ++num_futile_classifications;
if (segsearch_debug_level > 0) {
tprintf("num_futile_classifications %d\n", num_futile_classifications);
}
// Clean up
best_choice_bundle.updated = false;
delete pain_point; // done using this pain point
}
if (segsearch_debug_level > 0) {
tprintf("Done with SegSearch (AcceptableChoiceFound: %d\n",
language_model_->AcceptableChoiceFound());
}
// Clean up.
FreeHeapData(pain_points, MATRIX_COORD::Delete);
delete[] best_path_by_column;
delete[] pending;
for (row = 0; row < ratings->dimension(); ++row) {
for (col = 0; col <= row; ++col) {
BLOB_CHOICE_LIST *rating = ratings->get(col, row);
if (rating != NOT_CLASSIFIED) language_model_->DeleteState(rating);
}
}
}
/**********************************************************************
* merge_and_put_fragment_lists
*
* Merge the fragment lists in choice_lists and append it to the
* ratings matrix.
**********************************************************************/
void Wordrec::merge_and_put_fragment_lists(inT16 row, inT16 column,
inT16 num_frag_parts,
BLOB_CHOICE_LIST *choice_lists,
MATRIX *ratings) {
BLOB_CHOICE_IT *choice_lists_it = new BLOB_CHOICE_IT[num_frag_parts];
for (int i = 0; i < num_frag_parts; i++) {
choice_lists_it[i].set_to_list(&choice_lists[i]);
choice_lists_it[i].mark_cycle_pt();
}
BLOB_CHOICE_LIST *merged_choice = ratings->get(row, column);
if (merged_choice == NULL)
merged_choice = new BLOB_CHOICE_LIST;
bool end_of_list = false;
BLOB_CHOICE_IT merged_choice_it(merged_choice);
while (!end_of_list) {
// Find the maximum unichar_id of the current entry the iterators
// are pointing at
UNICHAR_ID max_unichar_id = choice_lists_it[0].data()->unichar_id();
for (int i = 0; i < num_frag_parts; i++) {
UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
if (max_unichar_id < unichar_id) {
max_unichar_id = unichar_id;
}
}
// Move the each iterators until it gets to an entry that has a
// value greater than or equal to max_unichar_id
for (int i = 0; i < num_frag_parts; i++) {
UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
while (!choice_lists_it[i].cycled_list() &&
unichar_id < max_unichar_id) {
choice_lists_it[i].forward();
unichar_id = choice_lists_it[i].data()->unichar_id();
}
if (choice_lists_it[i].cycled_list()) {
end_of_list = true;
break;
}
}
if (end_of_list)
break;
// Checks if the fragments are parts of the same character
UNICHAR_ID first_unichar_id = choice_lists_it[0].data()->unichar_id();
bool same_unichar = true;
for (int i = 1; i < num_frag_parts; i++) {
UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
if (unichar_id != first_unichar_id) {
same_unichar = false;
break;
}
}
if (same_unichar) {
// Add the merged character to the result
UNICHAR_ID merged_unichar_id = first_unichar_id;
inT16 merged_fontinfo_id = choice_lists_it[0].data()->fontinfo_id();
inT16 merged_fontinfo_id2 = choice_lists_it[0].data()->fontinfo_id2();
float merged_min_xheight = choice_lists_it[0].data()->min_xheight();
float merged_max_xheight = choice_lists_it[0].data()->max_xheight();
float positive_yshift = 0, negative_yshift = 0;
int merged_script_id = choice_lists_it[0].data()->script_id();
BlobChoiceClassifier classifier = choice_lists_it[0].data()->classifier();
float merged_rating = 0, merged_certainty = 0;
for (int i = 0; i < num_frag_parts; i++) {
float rating = choice_lists_it[i].data()->rating();
float certainty = choice_lists_it[i].data()->certainty();
if (i == 0 || certainty < merged_certainty)
merged_certainty = certainty;
merged_rating += rating;
choice_lists_it[i].forward();
if (choice_lists_it[i].cycled_list())
end_of_list = true;
IntersectRange(choice_lists_it[i].data()->min_xheight(),
choice_lists_it[i].data()->max_xheight(),
&merged_min_xheight, &merged_max_xheight);
float yshift = choice_lists_it[i].data()->yshift();
if (yshift > positive_yshift) positive_yshift = yshift;
if (yshift < negative_yshift) negative_yshift = yshift;
}
float merged_yshift = positive_yshift != 0
? (negative_yshift != 0 ? 0 : positive_yshift)
: negative_yshift;
merged_choice_it.add_to_end(new BLOB_CHOICE(merged_unichar_id,
merged_rating,
merged_certainty,
merged_fontinfo_id,
merged_fontinfo_id2,
merged_script_id,
merged_min_xheight,
merged_max_xheight,
merged_yshift,
classifier));
}
}
if (classify_debug_level)
print_ratings_list("Merged Fragments", merged_choice,
unicharset);
if (merged_choice->empty())
delete merged_choice;
else
ratings->put(row, column, merged_choice);
delete [] choice_lists_it;
}
