/**********************************************************************
* save_best_state
*
* Save this state away to be compared later.
**********************************************************************/
void save_best_state(CHUNKS_RECORD *chunks_record) {
STATE state;
SEARCH_STATE chunk_groups;
int num_joints;
if (save_priorities) {
num_joints = chunks_record->ratings->dimension() - 1;
state.part1 = 0xffffffff;
state.part2 = 0xffffffff;
chunk_groups = bin_to_chunks (&state, num_joints);
display_segmentation (chunks_record->chunks, chunk_groups);
memfree(chunk_groups);
cprintf ("Enter the correct segmentation > ");
fflush(stdout);
state.part1 = 0;
scanf ("%x", &state.part2);
chunk_groups = bin_to_chunks (&state, num_joints);
display_segmentation (chunks_record->chunks, chunk_groups);
memfree(chunk_groups);
window_wait(segm_window); /* == 'n') */
if (known_best_state)
free_state(known_best_state);
known_best_state = new_state (&state);
}
}
BLOB_CHOICE_LIST *Wordrec::classify_piece(TBLOB *pieces,
const DENORM& denorm,
SEAMS seams,
inT16 start,
inT16 end,
BlamerBundle *blamer_bundle) {
BLOB_CHOICE_LIST *choices;
TBLOB *blob;
inT16 x;
join_pieces(pieces, seams, start, end);
for (blob = pieces, x = 0; x < start; x++) {
blob = blob->next;
}
choices = classify_blob(blob, denorm, "pieces:", White, blamer_bundle);
break_pieces(blob, seams, start, end);
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations > 2) {
STATE current_state;
SEARCH_STATE chunk_groups;
set_n_ones (¤t_state, array_count(seams));
chunk_groups = bin_to_chunks(¤t_state, array_count(seams));
display_segmentation(pieces, chunk_groups);
window_wait(segm_window);
memfree(chunk_groups);
}
#endif
return (choices);
}
BLOB_CHOICE_LIST *Wordrec::classify_piece(TBLOB *pieces,
SEAMS seams,
inT16 start,
inT16 end) {
STATE current_state;
BLOB_CHOICE_LIST *choices;
TBLOB *pblob;
TBLOB *blob;
TBLOB *nblob;
inT16 x;
SEARCH_STATE chunk_groups;
set_n_ones (¤t_state, array_count (seams));
join_pieces(pieces, seams, start, end);
for (blob = pieces, pblob = NULL, x = 0; x < start; x++) {
pblob = blob;
blob = blob->next;
}
for (nblob = blob->next; x < end; x++)
nblob = nblob->next;
choices = classify_blob (pblob, blob, nblob, NULL, "pieces:", White);
break_pieces(blob, seams, start, end);
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations > 2) {
chunk_groups = bin_to_chunks (¤t_state, array_count (seams));
display_segmentation(pieces, chunk_groups);
window_wait(segm_window);
memfree(chunk_groups);
}
#endif
return (choices);
}
/**
* @name evaluate_state
*
* Evaluate the segmentation that is represented by this state in the
* best first search. Add this state to the "states_seen" list.
*/
inT16 Wordrec::evaluate_state(CHUNKS_RECORD *chunks_record,
SEARCH_RECORD *the_search,
DANGERR *fixpt) {
BLOB_CHOICE_LIST_VECTOR *char_choices;
SEARCH_STATE chunk_groups;
float rating_limit = the_search->best_choice->rating();
inT16 keep_going = TRUE;
PIECES_STATE widths;
the_search->num_states++;
chunk_groups = bin_to_chunks(the_search->this_state,
the_search->num_joints);
bin_to_pieces (the_search->this_state, the_search->num_joints, widths);
getDict().LogNewSegmentation(widths);
char_choices = evaluate_chunks(chunks_record, chunk_groups);
wordseg_rating_adjust_factor = -1.0f;
if (char_choices != NULL && char_choices->length() > 0) {
// Compute the segmentation cost and include the cost in word rating.
// TODO(dsl): We should change the SEARCH_RECORD to store this cost
// from state evaluation and avoid recomputing it here.
prioritize_state(chunks_record, the_search);
wordseg_rating_adjust_factor = the_search->segcost_bias;
getDict().permute_characters(*char_choices, rating_limit,
the_search->best_choice,
the_search->raw_choice);
bool replaced = false;
if (getDict().AcceptableChoice(char_choices, the_search->best_choice,
*(the_search->raw_choice), fixpt,
ASSOCIATOR_CALLER, &replaced)) {
keep_going = FALSE;
}
}
wordseg_rating_adjust_factor = -1.0f;
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations) {
display_segmentation (chunks_record->chunks, chunk_groups);
if (wordrec_display_segmentations > 1)
window_wait(segm_window);
}
#endif
if (rating_limit != the_search->best_choice->rating()) {
the_search->before_best = the_search->num_states;
the_search->best_state->part1 = the_search->this_state->part1;
the_search->best_state->part2 = the_search->this_state->part2;
replace_char_widths(chunks_record, chunk_groups);
}
else if (char_choices != NULL)
fixpt->index = -1;
if (char_choices != NULL) delete char_choices;
memfree(chunk_groups);
return (keep_going);
}
/**********************************************************************
* classify_piece
*
* Create a larger piece from a collection of smaller ones. Classify
* it and return the results. Take the large piece apart to leave
* the collection of small pieces un modified.
**********************************************************************/
CHOICES classify_piece(TBLOB *pieces,
SEAMS seams,
INT16 start,
INT16 end,
INT32 fx,
STATE *this_state,
STATE *best_state,
INT32 pass,
INT32 blob_index) {
STATE current_state;
CHOICES choices;
TBLOB *pblob;
TBLOB *blob;
TBLOB *nblob;
INT16 x;
SEARCH_STATE chunk_groups;
set_n_ones (¤t_state, array_count (seams));
join_pieces(pieces, seams, start, end);
for (blob = pieces, pblob = NULL, x = 0; x < start; x++) {
pblob = blob;
blob = blob->next;
}
for (nblob = blob->next; x < end; x++)
nblob = nblob->next;
choices = classify_blob (pblob, blob, nblob, NULL, fx, "pieces:", White,
this_state, best_state, pass, blob_index);
break_pieces(blob, seams, start, end);
#ifndef GRAPHICS_DISABLED
if (display_segmentations > 2) {
chunk_groups = bin_to_chunks (¤t_state, array_count (seams));
display_segmentation(pieces, chunk_groups);
window_wait(segm_window);
memfree(chunk_groups);
}
#endif
return (choices);
}
/**
* rebuild_current_state
*
* Transfers the given state to the word's output fields: rebuild_word,
* best_state, box_word, and returns the corresponding blob choices.
*/
BLOB_CHOICE_LIST_VECTOR *Wordrec::rebuild_current_state(
WERD_RES *word,
STATE *state,
BLOB_CHOICE_LIST_VECTOR *old_choices,
MATRIX *ratings) {
// Initialize search_state, num_joints, x, y.
int num_joints = array_count(word->seam_array);
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations) {
print_state("Rebuilding state", state, num_joints);
}
#endif
// Setup the rebuild_word ready for the output blobs.
if (word->rebuild_word != NULL)
delete word->rebuild_word;
word->rebuild_word = new TWERD;
// Setup the best_state.
word->best_state.clear();
SEARCH_STATE search_state = bin_to_chunks(state, num_joints);
// See which index is which below for information on x and y.
int x = 0;
int y;
for (int i = 1; i <= search_state[0]; i++) {
y = x + search_state[i];
x = y + 1;
}
y = count_blobs(word->chopped_word->blobs) - 1;
// Initialize char_choices, expanded_fragment_lengths:
// e.g. if fragment_lengths = {1 1 2 3 1},
// expanded_fragment_lengths_str = {1 1 2 2 3 3 3 1}.
BLOB_CHOICE_LIST_VECTOR *char_choices = new BLOB_CHOICE_LIST_VECTOR();
STRING expanded_fragment_lengths_str = "";
bool state_has_fragments = false;
const char *fragment_lengths = NULL;
if (word->best_choice->length() > 0) {
fragment_lengths = word->best_choice->fragment_lengths();
}
if (fragment_lengths) {
for (int i = 0; i < word->best_choice->length(); ++i) {
*char_choices += NULL;
word->best_state.push_back(0);
if (fragment_lengths[i] > 1) {
state_has_fragments = true;
}
for (int j = 0; j < fragment_lengths[i]; ++j) {
expanded_fragment_lengths_str += fragment_lengths[i];
}
}
} else {
for (int i = 0; i <= search_state[0]; ++i) {
expanded_fragment_lengths_str += (char)1;
*char_choices += NULL;
word->best_state.push_back(0);
}
}
// Set up variables for concatenating fragments.
const char *word_lengths_ptr = NULL;
const char *word_ptr = NULL;
if (state_has_fragments) {
// Make word_lengths_ptr point to the last element in
// best_choice->unichar_lengths().
word_lengths_ptr = word->best_choice->unichar_lengths().string();
word_lengths_ptr += (strlen(word_lengths_ptr)-1);
// Make word_str point to the beginning of the last
// unichar in best_choice->unichar_string().
word_ptr = word->best_choice->unichar_string().string();
word_ptr += (strlen(word_ptr)-*word_lengths_ptr);
}
const char *expanded_fragment_lengths =
expanded_fragment_lengths_str.string();
char unichar[UNICHAR_LEN + 1];
// Populate char_choices list such that it corresponds to search_state.
//
// If we are rebuilding a state that contains character fragments:
// -- combine blobs that belong to character fragments
// -- re-classify the blobs to obtain choices list for the merged blob
// -- ensure that correct classification appears in the new choices list
// NOTE: a choice composed form original fragment choices will be always
// added to the new choices list for each character composed from
// fragments (even if the choice for the corresponding character appears
// in the re-classified choices list of for the newly merged blob).
int ss_index = search_state[0];
// Which index is which?
// char_choices_index refers to the finished product: there is one for each
// blob/unicharset entry in the final word.
// ss_index refers to the search_state, and indexes a group (chunk) of blobs
// that were classified together for the best state.
// old_choice_index is a copy of ss_index, and accesses the old_choices,
// which correspond to chunks in the best state. old_choice_index gets
// set to -1 on a fragment set, as there is no corresponding chunk in
// the best state.
// x and y refer to the underlying blobs and are the first and last blob
// indices in a chunk.
for (int char_choices_index = char_choices->length() - 1;
char_choices_index >= 0;
--char_choices_index) {
// The start and end of the blob to rebuild.
int true_x = x;
int true_y = y;
// The fake merged fragment choice.
BLOB_CHOICE* merged_choice = NULL;
// Test for and combine fragments first.
int fragment_pieces = expanded_fragment_lengths[ss_index];
int old_choice_index = ss_index;
if (fragment_pieces > 1) {
strncpy(unichar, word_ptr, *word_lengths_ptr);
unichar[*word_lengths_ptr] = '\0';
merged_choice = rebuild_fragments(unichar, expanded_fragment_lengths,
old_choice_index, old_choices);
old_choice_index = -1;
}
while (fragment_pieces > 0) {
true_x = x;
// Move left to the previous blob.
y = x - 1;
x = y - search_state[ss_index--];
--fragment_pieces;
}
word->best_state[char_choices_index] = true_y + 1 - true_x;
BLOB_CHOICE_LIST *current_choices = join_blobs_and_classify(
word, true_x, true_y, old_choice_index, ratings, old_choices);
if (merged_choice != NULL) {
// Insert merged_blob into current_choices, such that current_choices
// are still sorted in non-descending order by rating.
ASSERT_HOST(!current_choices->empty());
BLOB_CHOICE_IT choice_it(current_choices);
for (choice_it.mark_cycle_pt(); !choice_it.cycled_list() &&
merged_choice->rating() > choice_it.data()->rating();
choice_it.forward())
choice_it.add_before_stay_put(merged_choice);
}
// Get rid of fragments in current_choices.
BLOB_CHOICE_IT choice_it(current_choices);
for (choice_it.mark_cycle_pt(); !choice_it.cycled_list();
choice_it.forward()) {
if (getDict().getUnicharset().get_fragment(
choice_it.data()->unichar_id())) {
delete choice_it.extract();
}
}
char_choices->set(current_choices, char_choices_index);
// Update word_ptr and word_lengths_ptr.
if (word_lengths_ptr != NULL && word_ptr != NULL) {
word_lengths_ptr--;
word_ptr -= (*word_lengths_ptr);
}
}
old_choices->delete_data_pointers();
delete old_choices;
memfree(search_state);
return char_choices;
}
/**
* @name evaluate_state
*
* Evaluate the segmentation that is represented by this state in the
* best first search. Add this state to the "states_seen" list.
*/
inT16 Wordrec::evaluate_state(CHUNKS_RECORD *chunks_record,
SEARCH_RECORD *the_search,
DANGERR *fixpt,
BlamerBundle *blamer_bundle) {
BLOB_CHOICE_LIST_VECTOR *char_choices;
SEARCH_STATE chunk_groups;
float rating_limit = the_search->best_choice->rating();
bool keep_going = true;
PIECES_STATE widths;
the_search->num_states++;
chunk_groups = bin_to_chunks(the_search->this_state,
the_search->num_joints);
bin_to_pieces (the_search->this_state, the_search->num_joints, widths);
if (wordrec_debug_level > 1) {
log_state("Evaluating state", the_search->num_joints,
the_search->this_state);
}
getDict().LogNewSegmentation(widths);
char_choices = evaluate_chunks(chunks_record, chunk_groups, blamer_bundle);
getDict().SetWordsegRatingAdjustFactor(-1.0f);
bool updated_best_choice = false;
if (char_choices != NULL && char_choices->length() > 0) {
// Compute the segmentation cost and include the cost in word rating.
// TODO(dsl): We should change the SEARCH_RECORD to store this cost
// from state evaluation and avoid recomputing it here.
prioritize_state(chunks_record, the_search);
getDict().SetWordsegRatingAdjustFactor(the_search->segcost_bias);
updated_best_choice =
getDict().permute_characters(*char_choices,
the_search->best_choice,
the_search->raw_choice);
bool replaced = false;
if (updated_best_choice) {
if (getDict().AcceptableChoice(char_choices, the_search->best_choice,
NULL, ASSOCIATOR_CALLER, &replaced)) {
keep_going = false;
}
CopyCharChoices(*char_choices, the_search->best_char_choices);
}
}
getDict().SetWordsegRatingAdjustFactor(-1.0f);
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations) {
display_segmentation (chunks_record->chunks, chunk_groups);
if (wordrec_display_segmentations > 1)
window_wait(segm_window);
}
#endif
if (rating_limit != the_search->best_choice->rating()) {
ASSERT_HOST(updated_best_choice);
the_search->before_best = the_search->num_states;
the_search->best_state->part1 = the_search->this_state->part1;
the_search->best_state->part2 = the_search->this_state->part2;
replace_char_widths(chunks_record, chunk_groups);
} else {
ASSERT_HOST(!updated_best_choice);
if (char_choices != NULL) fixpt->clear();
}
if (char_choices != NULL) delete char_choices;
memfree(chunk_groups);
return (keep_going);
}
/**
* rebuild_current_state
*
* Evaluate the segmentation that is represented by this state in the
* best first search. Add this state to the "states_seen" list.
*/
BLOB_CHOICE_LIST_VECTOR *Wordrec::rebuild_current_state(
TBLOB *blobs,
SEAMS seam_list,
STATE *state,
BLOB_CHOICE_LIST_VECTOR *old_choices,
int fx,
bool force_rebuild,
const WERD_CHOICE &best_choice,
const MATRIX *ratings) {
// Initialize search_state, num_joints, x, y.
int num_joints = array_count(seam_list);
#ifndef GRAPHICS_DISABLED
if (wordrec_display_segmentations) {
print_state("Rebuiling state", state, num_joints);
}
#endif
SEARCH_STATE search_state = bin_to_chunks(state, num_joints);
int x = 0;
int y;
int i;
for (i = 1; i <= search_state[0]; i++) {
y = x + search_state[i];
x = y + 1;
}
y = count_blobs (blobs) - 1;
// Initialize char_choices, expanded_fragment_lengths:
// e.g. if fragment_lengths = {1 1 2 3 1},
// expanded_fragment_lengths_str = {1 1 2 2 3 3 3 1}.
BLOB_CHOICE_LIST_VECTOR *char_choices = new BLOB_CHOICE_LIST_VECTOR();
STRING expanded_fragment_lengths_str = "";
bool state_has_fragments = false;
const char *fragment_lengths = NULL;
if (best_choice.length() > 0) {
fragment_lengths = best_choice.fragment_lengths();
}
if (fragment_lengths) {
for (int i = 0; i < best_choice.length(); ++i) {
*char_choices += NULL;
if (fragment_lengths[i] > 1) {
state_has_fragments = true;
}
for (int j = 0; j < fragment_lengths[i]; ++j) {
expanded_fragment_lengths_str += fragment_lengths[i];
}
}
} else {
for (i = 0; i <= search_state[0]; ++i) {
expanded_fragment_lengths_str += (char)1;
*char_choices += NULL;
}
}
// Finish early if force_rebuld is false and there are no fragments to merge.
if (!force_rebuild && !state_has_fragments) {
delete char_choices;
memfree(search_state);
return old_choices;
}
// Set up variables for concatenating fragments.
const char *word_lengths_ptr = NULL;
const char *word_ptr = NULL;
if (state_has_fragments) {
// Make word_lengths_ptr point to the last element in
// best_choice->unichar_lengths().
word_lengths_ptr = best_choice.unichar_lengths().string();
word_lengths_ptr += (strlen(word_lengths_ptr)-1);
// Make word_str point to the beginning of the last
// unichar in best_choice->unichar_string().
word_ptr = best_choice.unichar_string().string();
word_ptr += (strlen(word_ptr)-*word_lengths_ptr);
}
const char *expanded_fragment_lengths =
expanded_fragment_lengths_str.string();
bool merging_fragment = false;
int true_y = -1;
char unichar[UNICHAR_LEN + 1];
int fragment_pieces = -1;
float rating = 0.0;
float certainty = -MAX_FLOAT32;
// Populate char_choices list such that it corresponds to search_state.
//
// If we are rebuilding a state that contains character fragments:
// -- combine blobs that belong to character fragments
// -- re-classify the blobs to obtain choices list for the merged blob
// -- ensure that correct classification appears in the new choices list
// NOTE: a choice composed form original fragment choices will be always
// added to the new choices list for each character composed from
// fragments (even if the choice for the corresponding character appears
// in the re-classified choices list of for the newly merged blob).
BLOB_CHOICE_IT temp_it;
int char_choices_index = char_choices->length() - 1;
for (i = search_state[0]; i >= 0; i--) {
BLOB_CHOICE_LIST *current_choices = join_blobs_and_classify(
blobs, seam_list, x, y, fx, ratings, old_choices);
// Combine character fragments.
if (expanded_fragment_lengths[i] > 1) {
// Start merging character fragments.
if (!merging_fragment) {
merging_fragment = true;
true_y = y;
fragment_pieces = expanded_fragment_lengths[i];
rating = 0.0;
certainty = -MAX_FLOAT32;
strncpy(unichar, word_ptr, *word_lengths_ptr);
unichar[*word_lengths_ptr] = '\0';
}
// Take into account the fact that we could have joined pieces
// since we first recorded the ending point of a fragment (true_y).
true_y -= y - x;
// 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.
fragment_pieces--;
CHAR_FRAGMENT fragment;
fragment.set_all(unichar, fragment_pieces,
expanded_fragment_lengths[i]);
temp_it.set_to_list(current_choices);
for (temp_it.mark_cycle_pt(); !temp_it.cycled_list();
temp_it.forward()) {
const CHAR_FRAGMENT *current_fragment =
getDict().getUnicharset().get_fragment(temp_it.data()->unichar_id());
if (current_fragment && fragment.equals(current_fragment)) {
rating += temp_it.data()->rating();
if (temp_it.data()->certainty() > certainty) {
certainty = temp_it.data()->certainty();
}
break;
}
}
assert(!temp_it.cycled_list()); // make sure we found the fragment
// Free current_choices for the fragmented character.
delete current_choices;
// Finish composing character from fragments.
if (fragment_pieces == 0) {
// Populate current_choices with the classification of
// the blob merged from blobs of each character fragment.
current_choices = join_blobs_and_classify(blobs, seam_list, x,
true_y, fx, ratings, NULL);
BLOB_CHOICE *merged_choice =
new BLOB_CHOICE(getDict().getUnicharset().unichar_to_id(unichar),
rating, certainty, 0, NO_PERM);
// Insert merged_blob into current_choices, such that current_choices
// are still sorted in non-descending order by rating.
ASSERT_HOST(!current_choices->empty());
temp_it.set_to_list(current_choices);
for (temp_it.mark_cycle_pt();
!temp_it.cycled_list() &&
merged_choice->rating() > temp_it.data()->rating();
temp_it.forward());
temp_it.add_before_stay_put(merged_choice);
// Done merging this fragmented character.
merging_fragment = false;
}
}
if (!merging_fragment) {
// Get rid of fragments in current_choices.
temp_it.set_to_list(current_choices);
for (temp_it.mark_cycle_pt(); !temp_it.cycled_list();
temp_it.forward()) {
if (getDict().getUnicharset().get_fragment(
temp_it.data()->unichar_id())) {
delete temp_it.extract();
}
}
char_choices->set(current_choices, char_choices_index);
char_choices_index--;
// Update word_ptr and word_lengths_ptr.
if (word_lengths_ptr != NULL && word_ptr != NULL) {
word_lengths_ptr--;
word_ptr -= (*word_lengths_ptr);
}
}
y = x - 1;
x = y - search_state[i];
}
old_choices->delete_data_pointers();
delete old_choices;
memfree(search_state);
return (char_choices);
}
