// Returns a bigger MATRIX with a new column and row in the matrix in order
// to split the blob at the given (ind,ind) diagonal location.
// Entries are relocated to the new MATRIX using the transformation defined
// by MATRIX_COORD::MapForSplit.
// Transfers the pointer data to the new MATRIX and deletes *this.
MATRIX* MATRIX::ConsumeAndMakeBigger(int ind) {
int dim = dimension();
int band_width = bandwidth();
// Check to see if bandwidth needs expanding.
for (int col = ind; col >= 0 && col > ind - band_width; --col) {
if (array_[col * band_width + band_width - 1] != empty_) {
++band_width;
break;
}
}
MATRIX* result = new MATRIX(dim + 1, band_width);
for (int col = 0; col < dim; ++col) {
for (int row = col; row < dim && row < col + bandwidth(); ++row) {
MATRIX_COORD coord(col, row);
coord.MapForSplit(ind);
BLOB_CHOICE_LIST* choices = get(col, row);
if (choices != NULL) {
// Correct matrix location on each choice.
BLOB_CHOICE_IT bc_it(choices);
for (bc_it.mark_cycle_pt(); !bc_it.cycled_list(); bc_it.forward()) {
BLOB_CHOICE* choice = bc_it.data();
choice->set_matrix_cell(coord.col, coord.row);
}
ASSERT_HOST(coord.Valid(*result));
result->put(coord.col, coord.row, choices);
}
}
}
delete this;
return result;
}
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);
}
// Makes and returns a deep copy of *this, including all the BLOB_CHOICEs
// on the lists, but not any LanguageModelState that may be attached to the
// BLOB_CHOICEs.
MATRIX* MATRIX::DeepCopy() const {
int dim = dimension();
int band_width = bandwidth();
MATRIX* result = new MATRIX(dim, band_width);
for (int col = 0; col < dim; ++col) {
for (int row = col; row < dim && row < col + band_width; ++row) {
BLOB_CHOICE_LIST* choices = get(col, row);
if (choices != NULL) {
BLOB_CHOICE_LIST* copy_choices = new BLOB_CHOICE_LIST;
copy_choices->deep_copy(choices, &BLOB_CHOICE::deep_copy);
result->put(col, row, copy_choices);
}
}
}
return result;
}
/**********************************************************************
* record_piece_ratings
*
* Save the choices for all the pieces that have been classified into
* a matrix that can be used to look them up later. A two dimensional
* matrix is created. The indices correspond to the starting and
* ending initial piece number.
**********************************************************************/
MATRIX *Wordrec::record_piece_ratings(TBLOB *blobs) {
inT16 num_blobs = count_blobs(blobs);
TBOX *bounds = record_blob_bounds(blobs);
MATRIX *ratings = new MATRIX(num_blobs);
for (int x = 0; x < num_blobs; x++) {
for (int y = x; y < num_blobs; y++) {
TBOX piecebox = bounds_of_piece(bounds, x, y);
BLOB_CHOICE_LIST *choices = blob_match_table.get_match_by_box(piecebox);
if (choices != NULL) {
ratings->put(x, y, choices);
}
}
}
if (merge_fragments_in_matrix)
merge_fragments(ratings, num_blobs);
delete []bounds;
return ratings;
}
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);
}
}
}