// Sets flags necessary for recognition in the training mode.
// Opens and returns the pointer to the output file.
FILE *Tesseract::init_recog_training(const STRING &fname) {
if (tessedit_ambigs_training) {
tessedit_tess_adaption_mode.set_value(0); // turn off adaption
tessedit_enable_doc_dict.set_value(0); // turn off document dictionary
// Explore all segmentations.
getDict().stopper_no_acceptable_choices.set_value(1);
}
STRING output_fname = fname;
const char *lastdot = strrchr(output_fname.string(), '.');
if (lastdot != NULL) output_fname[lastdot - output_fname.string()] = '\0';
output_fname += ".txt";
FILE *output_file = open_file(output_fname.string(), "a+");
return output_file;
}
int main(int argc, char** argv)
{
FILE* fp; // declare dict file
char* programName = argv[0];
char* dictName = argv[1];
char* input = (char*)malloc(sizeof(char) * MAXLINE);
char* oldInput = (char*)malloc(sizeof(char) * MAXLINE);
if ((input == NULL) || (oldInput == NULL))
fprintf(stderr, MLCFAIL);
if ((fp = fopen(dictName, "r")) == NULL) {
fprintf(stderr, "%s: %s: No such file or directory\n",
programName, dictName);
// exit if dict is not loaded properly
return 1;
}
//build tree from dict
struct node* root = newNode();
root = getDict(fp, dictName, root);
fclose(fp);
// T9 interaction:
printf("Enter \"exit\" to quit.\n");
while (1) {
printf("Enter Key Sequence (or \"#\" for next word) :\n");
scanf("%s", input);
int len = strlen(input);
if (!strncmp(input, "exit", len))
break;
if (!strncmp(input, "#", 1))
strcat(oldInput, input);
else
strcpy(oldInput, input);
char* word = searchTrie(root, oldInput,
strlen(oldInput), 0);
printf("\t%s\n", word);
free(word); //free alloc from appendquotes
}
// clean up
free(input);
free(oldInput);
deleteTrie(root);
return 0;
}
/**
* @name program_editup
*
* Initialize all the things in the program that need to be initialized.
* init_permute determines whether to initialize the permute functions
* and Dawg models.
*/
void Wordrec::program_editup(const char *textbase, bool init_permute) {
if (textbase != NULL) {
imagefile = textbase;
/* Read in data files */
edit_with_ocr(textbase);
}
/* Initialize subsystems */
program_init();
mfeature_init(); // assumes that imagefile is initialized
if (init_permute)
getDict().init_permute();
setup_cp_maps();
init_metrics();
pass2_ok_split = chop_ok_split;
pass2_seg_states = wordrec_num_seg_states;
}
// Runs classify_word_pass1() on the current word. Outputs Tesseract's
// raw choice as a result of the classification. For words labeled with a
// single unichar also outputs all alternatives from blob_choices of the
// best choice.
void Tesseract::ambigs_classify_and_output(WERD_RES *werd_res,
ROW_RES *row_res,
BLOCK_RES *block_res,
const char *label,
FILE *output_file) {
int offset;
// Classify word.
fflush(stdout);
classify_word_pass1(block_res->block, row_res->row, werd_res);
WERD_CHOICE *best_choice = werd_res->best_choice;
ASSERT_HOST(best_choice != NULL);
ASSERT_HOST(best_choice->blob_choices() != NULL);
// Compute the number of unichars in the label.
int label_num_unichars = 0;
int step = 1; // should be non-zero on the first iteration
for (offset = 0; label[offset] != '\0' && step > 0;
step = werd_res->uch_set->step(label + offset),
offset += step, ++label_num_unichars);
if (step == 0) {
tprintf("Not outputting illegal unichar %s\n", label);
return;
}
// Output all classifier choices for the unigrams (1->1 classifications).
if (label_num_unichars == 1 && best_choice->blob_choices()->length() == 1) {
BLOB_CHOICE_LIST_C_IT outer_blob_choice_it;
outer_blob_choice_it.set_to_list(best_choice->blob_choices());
BLOB_CHOICE_IT blob_choice_it;
blob_choice_it.set_to_list(outer_blob_choice_it.data());
for (blob_choice_it.mark_cycle_pt();
!blob_choice_it.cycled_list();
blob_choice_it.forward()) {
BLOB_CHOICE *blob_choice = blob_choice_it.data();
if (blob_choice->unichar_id() != INVALID_UNICHAR_ID) {
fprintf(output_file, "%s\t%s\t%.4f\t%.4f\n",
unicharset.id_to_unichar(blob_choice->unichar_id()),
label, blob_choice->rating(), blob_choice->certainty());
}
}
}
// Output raw choices for many->many and 1->many classifications.
getDict().PrintAmbigAlternatives(output_file, label, label_num_unichars);
}
DECLARE_EXPORT void Skill::writeElement(XMLOutput *o, const Keyword& tag, mode m) const
{
// Write a reference
if (m == REFERENCE)
{
o->writeElement(tag, Tags::tag_name, getName());
return;
}
// Write the head
if (m != NOHEAD && m != NOHEADTAIL)
o->BeginObject(tag, Tags::tag_name, XMLEscape(getName()));
// Write source field
o->writeElement(Tags::tag_source, getSource());
// Write the custom fields
PythonDictionary::write(o, getDict());
// Write the tail
if (m != NOHEADTAIL && m != NOTAIL) o->EndObject(tag);
}
/**********************************************************************
* get_piece_rating
*
* Check to see if this piece has already been classified. If it has
* return that rating. Otherwise build the piece from the smaller
* pieces, classify it, store the rating for later, and take the piece
* apart again.
**********************************************************************/
BLOB_CHOICE_LIST *Wordrec::get_piece_rating(MATRIX *ratings,
TBLOB *blobs,
const DENORM& denorm,
SEAMS seams,
inT16 start,
inT16 end,
BlamerBundle *blamer_bundle) {
BLOB_CHOICE_LIST *choices = ratings->get(start, end);
if (choices == NOT_CLASSIFIED) {
choices = classify_piece(blobs,
denorm,
seams,
start,
end,
blamer_bundle);
ratings->put(start, end, choices);
if (wordrec_debug_level > 1) {
tprintf("get_piece_rating(): updated ratings matrix\n");
ratings->print(getDict().getUnicharset());
}
}
return (choices);
}
// Clear the document dictionary for this and all subclassifiers.
void Tesseract::ResetDocumentDictionary() {
getDict().ResetDocumentDictionary();
for (int i = 0; i < sub_langs_.size(); ++i) {
sub_langs_[i]->getDict().ResetDocumentDictionary();
}
}
/**
* @name program_editdown
*
* This function holds any necessary post processing for the Wise Owl
* program.
*/
void Wordrec::program_editdown(int32_t elasped_time) {
#ifndef DISABLED_LEGACY_ENGINE
EndAdaptiveClassifier();
#endif // ndef DISABLED_LEGACY_ENGINE
getDict().End();
}
/**
* @name dict_word()
*
* Test the dictionaries, returning NO_PERM (0) if not found, or one
* of the PermuterType values if found, according to the dictionary.
*/
int Wordrec::dict_word(const WERD_CHOICE &word) {
return getDict().valid_word(word);
}
/**
* @name improve_by_chopping
*
* Repeatedly chops the worst blob, classifying the new blobs fixing up all
* the data, and incrementally runs the segmentation search until a good word
* is found, or no more chops can be found.
*/
void Wordrec::improve_by_chopping(float rating_cert_scale,
WERD_RES* word,
BestChoiceBundle* best_choice_bundle,
BlamerBundle* blamer_bundle,
LMPainPoints* pain_points,
GenericVector<SegSearchPending>* pending) {
int blob_number;
do { // improvement loop.
// Make a simple vector of BLOB_CHOICEs to make it easy to pick which
// one to chop.
GenericVector<BLOB_CHOICE*> blob_choices;
int num_blobs = word->ratings->dimension();
for (int i = 0; i < num_blobs; ++i) {
BLOB_CHOICE_LIST* choices = word->ratings->get(i, i);
if (choices == NULL || choices->empty()) {
blob_choices.push_back(NULL);
} else {
BLOB_CHOICE_IT bc_it(choices);
blob_choices.push_back(bc_it.data());
}
}
SEAM* seam = improve_one_blob(blob_choices, &best_choice_bundle->fixpt,
false, false, word, &blob_number);
if (seam == NULL) break;
// A chop has been made. We have to correct all the data structures to
// take into account the extra bottom-level blob.
// Put the seam into the seam_array and correct everything else on the
// word: ratings matrix (including matrix location in the BLOB_CHOICES),
// states in WERD_CHOICEs, and blob widths.
word->InsertSeam(blob_number, seam);
// Insert a new entry in the beam array.
best_choice_bundle->beam.insert(new LanguageModelState, blob_number);
// Fixpts are outdated, but will get recalculated.
best_choice_bundle->fixpt.clear();
// Remap existing pain points.
pain_points->RemapForSplit(blob_number);
// Insert a new pending at the chop point.
pending->insert(SegSearchPending(), blob_number);
// Classify the two newly created blobs using ProcessSegSearchPainPoint,
// as that updates the pending correctly and adds new pain points.
MATRIX_COORD pain_point(blob_number, blob_number);
ProcessSegSearchPainPoint(0.0f, pain_point, "Chop1", pending, word,
pain_points, blamer_bundle);
pain_point.col = blob_number + 1;
pain_point.row = blob_number + 1;
ProcessSegSearchPainPoint(0.0f, pain_point, "Chop2", pending, word,
pain_points, blamer_bundle);
if (language_model_->language_model_ngram_on) {
// N-gram evaluation depends on the number of blobs in a chunk, so we
// have to re-evaluate everything in the word.
ResetNGramSearch(word, best_choice_bundle, pending);
blob_number = 0;
}
// Run language model incrementally. (Except with the n-gram model on.)
UpdateSegSearchNodes(rating_cert_scale, blob_number, pending,
word, pain_points, best_choice_bundle, blamer_bundle);
} while (!language_model_->AcceptableChoiceFound() &&
word->ratings->dimension() < kMaxNumChunks);
// If after running only the chopper best_choice is incorrect and no blame
// has been yet set, blame the classifier if best_choice is classifier's
// top choice and is a dictionary word (i.e. language model could not have
// helped). Otherwise blame the tradeoff between the classifier and
// the old language model (permuters).
if (word->blamer_bundle != NULL &&
word->blamer_bundle->incorrect_result_reason() == IRR_CORRECT &&
!word->blamer_bundle->ChoiceIsCorrect(word->best_choice)) {
bool valid_permuter = word->best_choice != NULL &&
Dict::valid_word_permuter(word->best_choice->permuter(), false);
word->blamer_bundle->BlameClassifierOrLangModel(word,
getDict().getUnicharset(),
valid_permuter,
wordrec_debug_blamer);
}
}
/**
* @name tess_acceptable_word
*
* @return true if the word is regarded as "good enough".
* @param word_choice after context
* @param raw_choice before context
*/
bool Tesseract::tess_acceptable_word(WERD_RES* word) {
return getDict().AcceptableResult(word);
}
/**
* 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 program_editdown
*
* This function holds any nessessary post processing for the Wise Owl
* program.
*/
void Wordrec::program_editdown(inT32 elasped_time) {
EndAdaptiveClassifier();
getDict().End();
}
BOOL8 Tesseract::word_adaptable( //should we adapt?
WERD_RES *word,
uinT16 mode) {
if (tessedit_adaption_debug) {
tprintf("Running word_adaptable() for %s rating %.4f certainty %.4f\n",
word->best_choice == NULL ? "" :
word->best_choice->unichar_string().string(),
word->best_choice->rating(), word->best_choice->certainty());
}
BOOL8 status = FALSE;
BITS16 flags(mode);
enum MODES
{
ADAPTABLE_WERD,
ACCEPTABLE_WERD,
CHECK_DAWGS,
CHECK_SPACES,
CHECK_ONE_ELL_CONFLICT,
CHECK_AMBIG_WERD
};
/*
0: NO adaption
*/
if (mode == 0) {
if (tessedit_adaption_debug) tprintf("adaption disabled\n");
return FALSE;
}
if (flags.bit (ADAPTABLE_WERD)) {
status |= word->tess_would_adapt; // result of Classify::AdaptableWord()
if (tessedit_adaption_debug && !status) {
tprintf("tess_would_adapt bit is false\n");
}
}
if (flags.bit (ACCEPTABLE_WERD)) {
status |= word->tess_accepted;
if (tessedit_adaption_debug && !status) {
tprintf("tess_accepted bit is false\n");
}
}
if (!status) { // If not set then
return FALSE; // ignore other checks
}
if (flags.bit (CHECK_DAWGS) &&
(word->best_choice->permuter () != SYSTEM_DAWG_PERM) &&
(word->best_choice->permuter () != FREQ_DAWG_PERM) &&
(word->best_choice->permuter () != USER_DAWG_PERM) &&
(word->best_choice->permuter () != NUMBER_PERM)) {
if (tessedit_adaption_debug) tprintf("word not in dawgs\n");
return FALSE;
}
if (flags.bit (CHECK_ONE_ELL_CONFLICT) && one_ell_conflict (word, FALSE)) {
if (tessedit_adaption_debug) tprintf("word has ell conflict\n");
return FALSE;
}
if (flags.bit (CHECK_SPACES) &&
(strchr(word->best_choice->unichar_string().string(), ' ') != NULL)) {
if (tessedit_adaption_debug) tprintf("word contains spaces\n");
return FALSE;
}
// if (flags.bit (CHECK_AMBIG_WERD) && test_ambig_word (word))
if (flags.bit (CHECK_AMBIG_WERD) &&
!getDict().NoDangerousAmbig(word->best_choice, NULL, false, NULL, NULL)) {
if (tessedit_adaption_debug) tprintf("word is ambiguous\n");
return FALSE;
}
// Do not adapt to words that are composed from fragments if
// tessedit_adapt_to_char_fragments is false.
if (!tessedit_adapt_to_char_fragments) {
const char *fragment_lengths = word->best_choice->fragment_lengths();
if (fragment_lengths != NULL && *fragment_lengths != '\0') {
for (int i = 0; i < word->best_choice->length(); ++i) {
if (fragment_lengths[i] > 1) {
if (tessedit_adaption_debug) tprintf("won't adapt to fragments\n");
return false; // found a character composed from fragments
}
}
}
}
if (tessedit_adaption_debug) {
tprintf("returning status %d\n", status);
}
return status;
}
void
mkraddobjects()
{
AcGePoint3d pt;
if (RTNORM != acedGetPoint( NULL, "\nEnter position:", asDblArray (pt) ))
return;
AsdkMkrEntity* pEnt = new AsdkMkrEntity;
if (NULL == pEnt)
return;
pEnt->setPos( pt );
if (!append( pEnt )) {
delete pEnt;
return;
}
AcDbObjectId objId;
AsdkMkrObject *pObj = new AsdkMkrObject;
if (NULL == pObj) {
pEnt->erase();
pEnt->close();
return;
}
#ifdef DIRECT
acdbHostApplicationServices()->workingDatabase()
->addAcDbObject( objId, pObj );
pObj->close();
#else
#ifdef NOD
AcDbDictionary* pMyDict = getDict( /*NOXLATE*/"ASDK_MYDICT", AcDb::kForWrite );
if (NULL != pMyDict)
pMyDict->setMergeStyle(AcDb::kDrcMangleName);
#else
AcDbDictionary* pMyDict = getExtDict( pEnt, /*NOXLATE*/"ASDK_MYDICT", AcDb::kForWrite );
#endif // NOD
if (NULL == pMyDict) {
delete pObj;
pEnt->erase();
pEnt->close();
return;
}
Acad::ErrorStatus es;
if (pMyDict->has( /*NOXLATE*/"MYENTRY" ))
es = pMyDict->setAt( "*", pObj, objId );
else
es = pMyDict->setAt( /*NOXLATE*/"MYENTRY", pObj, objId );
pMyDict->close();
if (Acad::eOk == es)
pObj->close();
else {
delete pObj;
pEnt->erase();
pEnt->close();
return;
}
#endif // DIRECT
pEnt->setId( objId );
pEnt->close();
acutPrintf( "\nEv'rything OK\n" );
}
// Apply segmentation search to the given set of words, within the constraints
// of the existing ratings matrix. If there is already a best_choice on a word
// leaves it untouched and just sets the done/accepted etc flags.
void Tesseract::SearchWords(PointerVector<WERD_RES>* words) {
// Run the segmentation search on the network outputs and make a BoxWord
// for each of the output words.
// If we drop a word as junk, then there is always a space in front of the
// next.
const Dict* stopper_dict = lstm_recognizer_->GetDict();
if (stopper_dict == nullptr) stopper_dict = &getDict();
bool any_nonspace_delimited = false;
for (int w = 0; w < words->size(); ++w) {
WERD_RES* word = (*words)[w];
if (word->best_choice != nullptr &&
word->best_choice->ContainsAnyNonSpaceDelimited()) {
any_nonspace_delimited = true;
break;
}
}
for (int w = 0; w < words->size(); ++w) {
WERD_RES* word = (*words)[w];
if (word->best_choice == NULL) {
// If we are using the beam search, the unicharset had better match!
word->SetupWordScript(unicharset);
WordSearch(word);
} else if (word->best_choice->unicharset() == &unicharset &&
!lstm_recognizer_->IsRecoding()) {
// We set up the word without using the dictionary, so set the permuter
// now, but we can only do it because the unicharsets match.
word->best_choice->set_permuter(
getDict().valid_word(*word->best_choice, true));
}
if (word->best_choice == NULL) {
// It is a dud.
word->SetupFake(lstm_recognizer_->GetUnicharset());
} else {
// Set the best state.
for (int i = 0; i < word->best_choice->length(); ++i) {
int length = word->best_choice->state(i);
word->best_state.push_back(length);
}
word->reject_map.initialise(word->best_choice->length());
word->tess_failed = false;
word->tess_accepted = true;
word->tess_would_adapt = false;
word->done = true;
word->tesseract = this;
float word_certainty = MIN(word->space_certainty,
word->best_choice->certainty());
word_certainty *= kCertaintyScale;
// Arbitrary ding factor for non-dictionary words.
if (!lstm_recognizer_->IsRecoding() &&
!Dict::valid_word_permuter(word->best_choice->permuter(), true))
word_certainty -= kNonDictionaryPenalty;
if (getDict().stopper_debug_level >= 1) {
tprintf("Best choice certainty=%g, space=%g, scaled=%g, final=%g\n",
word->best_choice->certainty(), word->space_certainty,
MIN(word->space_certainty, word->best_choice->certainty()) *
kCertaintyScale,
word_certainty);
word->best_choice->print();
}
// Discard words that are impossibly bad, but allow a bit more for
// dictionary words, and keep bad words in non-space-delimited langs.
if (word_certainty >= RecodeBeamSearch::kMinCertainty ||
any_nonspace_delimited ||
(word_certainty >= kWorstDictCertainty &&
Dict::valid_word_permuter(word->best_choice->permuter(), true))) {
word->tess_accepted = stopper_dict->AcceptableResult(word);
} else {
if (getDict().stopper_debug_level >= 1) {
tprintf("Deleting word with certainty %g\n", word_certainty);
word->best_choice->print();
}
// It is a dud.
word->SetupFake(lstm_recognizer_->GetUnicharset());
}
word->best_choice->set_certainty(word_certainty);
}
}
}
/**
* @name chop_word_main
*
* Classify the blobs in this word and permute the results. Find the
* worst blob in the word and chop it up. Continue this process until
* a good answer has been found or all the blobs have been chopped up
* enough. Return the word level ratings.
*/
BLOB_CHOICE_LIST_VECTOR *Wordrec::chop_word_main(WERD_RES *word) {
TBLOB *blob;
int index;
int did_chopping;
STATE state;
BLOB_CHOICE_LIST *match_result;
MATRIX *ratings = NULL;
DANGERR fixpt; /*dangerous ambig */
inT32 bit_count; //no of bits
set_denorm(&word->denorm);
BLOB_CHOICE_LIST_VECTOR *char_choices = new BLOB_CHOICE_LIST_VECTOR();
BLOB_CHOICE_LIST_VECTOR *best_char_choices = new BLOB_CHOICE_LIST_VECTOR();
did_chopping = 0;
for (blob = word->chopped_word->blobs, index = 0;
blob != NULL; blob = blob->next, index++) {
match_result = classify_blob(blob, "chop_word:", Green);
if (match_result == NULL)
cprintf("Null classifier output!\n");
*char_choices += match_result;
}
bit_count = index - 1;
set_n_ones(&state, char_choices->length() - 1);
bool acceptable = false;
bool replaced = false;
bool best_choice_updated =
getDict().permute_characters(*char_choices, word->best_choice,
word->raw_choice);
if (best_choice_updated &&
getDict().AcceptableChoice(char_choices, word->best_choice, &fixpt,
CHOPPER_CALLER, &replaced)) {
acceptable = true;
}
if (replaced)
update_blob_classifications(word->chopped_word, *char_choices);
CopyCharChoices(*char_choices, best_char_choices);
if (!acceptable) { // do more work to find a better choice
did_chopping = 1;
bool best_choice_acceptable = false;
if (chop_enable)
improve_by_chopping(word,
char_choices,
&state,
best_char_choices,
&fixpt,
&best_choice_acceptable);
if (chop_debug)
print_seams ("Final seam list:", word->seam_array);
// The force_word_assoc is almost redundant to enable_assoc. However,
// it is not conditioned on the dict behavior. For CJK, we need to force
// the associator to be invoked. When we figure out the exact behavior
// of dict on CJK, we can remove the flag if it turns out to be redundant.
if ((wordrec_enable_assoc && !best_choice_acceptable) || force_word_assoc) {
ratings = word_associator(word, &state, best_char_choices,
&fixpt, &state);
}
}
best_char_choices = rebuild_current_state(word, &state, best_char_choices,
ratings);
if (ratings != NULL) {
if (wordrec_debug_level > 0) {
tprintf("Final Ratings Matrix:\n");
ratings->print(getDict().getUnicharset());
}
ratings->delete_matrix_pointers();
delete ratings;
}
getDict().FilterWordChoices();
char_choices->delete_data_pointers();
delete char_choices;
return best_char_choices;
}
/**********************************************************************
* tess_acceptable_word
*
* Return true if the word is regarded as "good enough".
**********************************************************************/
BOOL8 Tesseract::tess_acceptable_word(
WERD_CHOICE *word_choice, // after context
WERD_CHOICE *raw_choice) { // before context
return getDict().AcceptableResult(*word_choice, *raw_choice);
}
/**
* @name program_editdown
*
* This function holds any nessessary post processing for the Wise Owl
* program.
*/
void Wordrec::program_editdown(inT32 elasped_time) {
EndAdaptiveClassifier();
blob_match_table.end_match_table();
getDict().InitChoiceAccum();
getDict().End();
}
Wordrec::Wordrec() :
// control parameters
BOOL_MEMBER(merge_fragments_in_matrix, TRUE,
"Merge the fragments in the ratings matrix and delete them"
" after merging", params()),
BOOL_MEMBER(wordrec_no_block, FALSE, "Don't output block information",
params()),
BOOL_MEMBER(wordrec_enable_assoc, TRUE, "Associator Enable",
params()),
BOOL_MEMBER(force_word_assoc, FALSE,
"force associator to run regardless of what enable_assoc is."
"This is used for CJK where component grouping is necessary.",
CCUtil::params()),
INT_MEMBER(wordrec_num_seg_states, 30, "Segmentation states",
CCUtil::params()),
double_MEMBER(wordrec_worst_state, 1.0, "Worst segmentation state",
params()),
BOOL_MEMBER(fragments_guide_chopper, FALSE,
"Use information from fragments to guide chopping process",
params()),
INT_MEMBER(repair_unchopped_blobs, 1, "Fix blobs that aren't chopped",
params()),
double_MEMBER(tessedit_certainty_threshold, -2.25, "Good blob limit",
params()),
INT_MEMBER(chop_debug, 0, "Chop debug",
params()),
BOOL_MEMBER(chop_enable, 1, "Chop enable",
params()),
BOOL_MEMBER(chop_vertical_creep, 0, "Vertical creep",
params()),
INT_MEMBER(chop_split_length, 10000, "Split Length",
params()),
INT_MEMBER(chop_same_distance, 2, "Same distance",
params()),
INT_MEMBER(chop_min_outline_points, 6, "Min Number of Points on Outline",
params()),
INT_MEMBER(chop_inside_angle, -50, "Min Inside Angle Bend",
params()),
INT_MEMBER(chop_min_outline_area, 2000, "Min Outline Area",
params()),
double_MEMBER(chop_split_dist_knob, 0.5, "Split length adjustment",
params()),
double_MEMBER(chop_overlap_knob, 0.9, "Split overlap adjustment",
params()),
double_MEMBER(chop_center_knob, 0.15, "Split center adjustment",
params()),
double_MEMBER(chop_sharpness_knob, 0.06, "Split sharpness adjustment",
params()),
double_MEMBER(chop_width_change_knob, 5.0, "Width change adjustment",
params()),
double_MEMBER(chop_ok_split, 100.0, "OK split limit",
params()),
double_MEMBER(chop_good_split, 50.0, "Good split limit",
params()),
INT_MEMBER(chop_x_y_weight, 3, "X / Y length weight",
params()),
INT_MEMBER(segment_adjust_debug, 0, "Segmentation adjustment debug",
params()),
BOOL_MEMBER(assume_fixed_pitch_char_segment, FALSE,
"include fixed-pitch heuristics in char segmentation",
params()),
BOOL_MEMBER(use_new_state_cost, FALSE,
"use new state cost heuristics for segmentation state evaluation",
params()),
double_MEMBER(heuristic_segcost_rating_base, 1.25,
"base factor for adding segmentation cost into word rating."
"It's a multiplying factor, the larger the value above 1, "
"the bigger the effect of segmentation cost.",
params()),
double_MEMBER(heuristic_weight_rating, 1.0,
"weight associated with char rating in combined cost of state",
params()),
double_MEMBER(heuristic_weight_width, 1000.0,
"weight associated with width evidence in combined cost of"
" state", params()),
double_MEMBER(heuristic_weight_seamcut, 0.0,
"weight associated with seam cut in combined cost of state",
params()),
double_MEMBER(heuristic_max_char_wh_ratio, 2.0,
"max char width-to-height ratio allowed in segmentation",
params()),
INT_MEMBER(wordrec_debug_level, 0,
"Debug level for wordrec", params()),
BOOL_MEMBER(wordrec_debug_blamer, false,
"Print blamer debug messages", params()),
BOOL_MEMBER(wordrec_run_blamer, false,
"Try to set the blame for errors", params()),
BOOL_MEMBER(enable_new_segsearch, true,
"Enable new segmentation search path.", params()),
INT_MEMBER(segsearch_debug_level, 0,
"SegSearch debug level", params()),
INT_MEMBER(segsearch_max_pain_points, 2000,
"Maximum number of pain points stored in the queue",
params()),
INT_MEMBER(segsearch_max_futile_classifications, 10,
"Maximum number of pain point classifications per word that"
"did not result in finding a better word choice.",
params()),
double_MEMBER(segsearch_max_char_wh_ratio, 2.0,
"Maximum character width-to-height ratio", params()),
double_MEMBER(segsearch_max_fixed_pitch_char_wh_ratio, 2.0,
"Maximum character width-to-height ratio for"
" fixed-pitch fonts",
params()),
BOOL_MEMBER(save_alt_choices, false,
"Save alternative paths found during chopping"
" and segmentation search",
params()) {
prev_word_best_choice_ = NULL;
language_model_ = new LanguageModel(&get_fontinfo_table(),
&(getDict()));
pass2_seg_states = 0;
num_joints = 0;
num_pushed = 0;
num_popped = 0;
fill_lattice_ = NULL;
}
/**
* @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);
}
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);
}
}
}
/*************************************************************************
* write_results()
*
* All recognition and rejection has now been done. Generate the following:
* .txt file - giving the final best choices with NO highlighting
* .raw file - giving the tesseract top choice output for each word
* .map file - showing how the .txt file has been rejected in the .ep file
* epchoice list - a list of one element per word, containing the text for the
* epaper. Reject strings are inserted.
* inset list - a list of bounding boxes of reject insets - indexed by the
* reject strings in the epchoice text.
*************************************************************************/
void Tesseract::write_results(PAGE_RES_IT &page_res_it,
char newline_type, // type of newline
BOOL8 force_eol) { // override tilde crunch?
WERD_RES *word = page_res_it.word();
STRING repetition_code;
const STRING *wordstr;
STRING wordstr_lengths;
int i;
char unrecognised = STRING (unrecognised_char)[0];
char ep_chars[32]; //Only for unlv_tilde_crunch
int ep_chars_index = 0;
char txt_chs[32]; //Only for unlv_tilde_crunch
char map_chs[32]; //Only for unlv_tilde_crunch
int txt_index = 0;
BOOL8 need_reject = FALSE;
UNICHAR_ID space = unicharset.unichar_to_id(" ");
if ((word->unlv_crunch_mode != CR_NONE ||
word->best_choice->length() == 0) &&
!tessedit_zero_kelvin_rejection && !tessedit_word_for_word) {
if ((word->unlv_crunch_mode != CR_DELETE) &&
(!stats_.tilde_crunch_written ||
((word->unlv_crunch_mode == CR_KEEP_SPACE) &&
(word->word->space () > 0) &&
!word->word->flag (W_FUZZY_NON) &&
!word->word->flag (W_FUZZY_SP)))) {
if (!word->word->flag (W_BOL) &&
(word->word->space () > 0) &&
!word->word->flag (W_FUZZY_NON) &&
!word->word->flag (W_FUZZY_SP)) {
// Write a space to separate from preceeding good text.
txt_chs[txt_index] = ' ';
map_chs[txt_index++] = '1';
ep_chars[ep_chars_index++] = ' ';
stats_.last_char_was_tilde = false;
}
need_reject = TRUE;
}
if ((need_reject && !stats_.last_char_was_tilde) ||
(force_eol && stats_.write_results_empty_block)) {
/* Write a reject char - mark as rejected unless zero_rejection mode */
stats_.last_char_was_tilde = TRUE;
txt_chs[txt_index] = unrecognised;
if (tessedit_zero_rejection || (suspect_level == 0)) {
map_chs[txt_index++] = '1';
ep_chars[ep_chars_index++] = unrecognised;
}
else {
map_chs[txt_index++] = '0';
/*
The ep_choice string is a faked reject to allow newdiff to sync the
.etx with the .txt and .map files.
*/
ep_chars[ep_chars_index++] = CTRL_INSET; // escape code
//dummy reject
ep_chars[ep_chars_index++] = 1;
//dummy reject
ep_chars[ep_chars_index++] = 1;
//type
ep_chars[ep_chars_index++] = 2;
//dummy reject
ep_chars[ep_chars_index++] = 1;
//dummy reject
ep_chars[ep_chars_index++] = 1;
}
stats_.tilde_crunch_written = true;
stats_.last_char_was_newline = false;
stats_.write_results_empty_block = false;
}
if ((word->word->flag (W_EOL) && !stats_.last_char_was_newline) || force_eol) {
/* Add a new line output */
txt_chs[txt_index] = '\n';
map_chs[txt_index++] = '\n';
//end line
ep_chars[ep_chars_index++] = newline_type;
//Cos of the real newline
stats_.tilde_crunch_written = false;
stats_.last_char_was_newline = true;
stats_.last_char_was_tilde = false;
}
txt_chs[txt_index] = '\0';
map_chs[txt_index] = '\0';
ep_chars[ep_chars_index] = '\0'; // terminate string
word->ep_choice = new WERD_CHOICE(ep_chars, unicharset);
if (force_eol)
stats_.write_results_empty_block = true;
return;
}
/* NORMAL PROCESSING of non tilde crunched words */
stats_.tilde_crunch_written = false;
if (newline_type)
stats_.last_char_was_newline = true;
else
stats_.last_char_was_newline = false;
stats_.write_results_empty_block = force_eol; // about to write a real word
if (unlv_tilde_crunching &&
stats_.last_char_was_tilde &&
(word->word->space() == 0) &&
!(word->word->flag(W_REP_CHAR) && tessedit_write_rep_codes) &&
(word->best_choice->unichar_id(0) == space)) {
/* Prevent adjacent tilde across words - we know that adjacent tildes within
words have been removed */
word->best_choice->remove_unichar_id(0);
if (word->best_choice->blob_choices() != NULL) {
BLOB_CHOICE_LIST_C_IT blob_choices_it(word->best_choice->blob_choices());
if (!blob_choices_it.empty()) delete blob_choices_it.extract();
}
word->best_choice->populate_unichars(getDict().getUnicharset());
word->reject_map.remove_pos (0);
delete word->box_word;
word->box_word = new BoxWord;
}
if (newline_type ||
(word->word->flag (W_REP_CHAR) && tessedit_write_rep_codes))
stats_.last_char_was_tilde = false;
else {
if (word->reject_map.length () > 0) {
if (word->best_choice->unichar_id(word->reject_map.length() - 1) == space)
stats_.last_char_was_tilde = true;
else
stats_.last_char_was_tilde = false;
}
else if (word->word->space () > 0)
stats_.last_char_was_tilde = false;
/* else it is unchanged as there are no output chars */
}
ASSERT_HOST (word->best_choice->length() == word->reject_map.length());
set_unlv_suspects(word);
check_debug_pt (word, 120);
if (tessedit_rejection_debug) {
tprintf ("Dict word: \"%s\": %d\n",
word->best_choice->debug_string(unicharset).string(),
dict_word(*(word->best_choice)));
}
if (word->word->flag (W_REP_CHAR) && tessedit_write_rep_codes) {
repetition_code = "|^~R";
wordstr_lengths = "\001\001\001\001";
repetition_code += unicharset.id_to_unichar(get_rep_char (word));
wordstr_lengths += strlen(unicharset.id_to_unichar(get_rep_char (word)));
wordstr = &repetition_code;
} else {
if (tessedit_zero_rejection) {
/* OVERRIDE ALL REJECTION MECHANISMS - ONLY REJECT TESS FAILURES */
for (i = 0; i < word->best_choice->length(); ++i) {
if (word->reject_map[i].rejected())
word->reject_map[i].setrej_minimal_rej_accept();
}
}
if (tessedit_minimal_rejection) {
/* OVERRIDE ALL REJECTION MECHANISMS - ONLY REJECT TESS FAILURES */
for (i = 0; i < word->best_choice->length(); ++i) {
if ((word->best_choice->unichar_id(i) != space) &&
word->reject_map[i].rejected())
word->reject_map[i].setrej_minimal_rej_accept();
}
}
}
}
/// Recursive helper to find a match to the target_text (from text_index
/// position) in the choices (from choices_pos position).
/// @param choices is an array of GenericVectors, of length choices_length,
/// with each element representing a starting position in the word, and the
/// #GenericVector holding classification results for a sequence of consecutive
/// blobs, with index 0 being a single blob, index 1 being 2 blobs etc.
/// @param choices_pos
/// @param choices_length
/// @param target_text
/// @param text_index
/// @param rating
/// @param segmentation
/// @param best_rating
/// @param best_segmentation
void Tesseract::SearchForText(const GenericVector<BLOB_CHOICE_LIST*>* choices,
int choices_pos, int choices_length,
const GenericVector<UNICHAR_ID>& target_text,
int text_index,
float rating, GenericVector<int>* segmentation,
float* best_rating,
GenericVector<int>* best_segmentation) {
const UnicharAmbigsVector& table = getDict().getUnicharAmbigs().dang_ambigs();
for (int length = 1; length <= choices[choices_pos].size(); ++length) {
// Rating of matching choice or worst choice if no match.
float choice_rating = 0.0f;
// Find the corresponding best BLOB_CHOICE.
BLOB_CHOICE_IT choice_it(choices[choices_pos][length - 1]);
for (choice_it.mark_cycle_pt(); !choice_it.cycled_list();
choice_it.forward()) {
BLOB_CHOICE* choice = choice_it.data();
choice_rating = choice->rating();
UNICHAR_ID class_id = choice->unichar_id();
if (class_id == target_text[text_index]) {
break;
}
// Search ambigs table.
if (class_id < table.size() && table[class_id] != NULL) {
AmbigSpec_IT spec_it(table[class_id]);
for (spec_it.mark_cycle_pt(); !spec_it.cycled_list();
spec_it.forward()) {
const AmbigSpec *ambig_spec = spec_it.data();
// We'll only do 1-1.
if (ambig_spec->wrong_ngram[1] == INVALID_UNICHAR_ID &&
ambig_spec->correct_ngram_id == target_text[text_index])
break;
}
if (!spec_it.cycled_list())
break; // Found an ambig.
}
}
if (choice_it.cycled_list())
continue; // No match.
segmentation->push_back(length);
if (choices_pos + length == choices_length &&
text_index + 1 == target_text.size()) {
// This is a complete match. If the rating is good record a new best.
if (applybox_debug > 2) {
tprintf("Complete match, rating = %g, best=%g, seglength=%d, best=%d\n",
rating + choice_rating, *best_rating, segmentation->size(),
best_segmentation->size());
}
if (best_segmentation->empty() || rating + choice_rating < *best_rating) {
*best_segmentation = *segmentation;
*best_rating = rating + choice_rating;
}
} else if (choices_pos + length < choices_length &&
text_index + 1 < target_text.size()) {
if (applybox_debug > 3) {
tprintf("Match found for %d=%s:%s, at %d+%d, recursing...\n",
target_text[text_index],
unicharset.id_to_unichar(target_text[text_index]),
choice_it.data()->unichar_id() == target_text[text_index]
? "Match" : "Ambig",
choices_pos, length);
}
SearchForText(choices, choices_pos + length, choices_length, target_text,
text_index + 1, rating + choice_rating, segmentation,
best_rating, best_segmentation);
if (applybox_debug > 3) {
tprintf("End recursion for %d=%s\n", target_text[text_index],
unicharset.id_to_unichar(target_text[text_index]));
}
}
segmentation->truncate(segmentation->size() - 1);
}
}
/**
* @name tess_add_doc_word
*
* Add the given word to the document dictionary
*/
void Tesseract::tess_add_doc_word(WERD_CHOICE *word_choice) {
getDict().add_document_word(*word_choice);
}
/**
* 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);
}
/**********************************************************************
* select_blob_to_split
*
* These are the results of the last classification. Find a likely
* place to apply splits. If none, return -1.
**********************************************************************/
int Wordrec::select_blob_to_split(
const GenericVector<BLOB_CHOICE*>& blob_choices,
float rating_ceiling, bool split_next_to_fragment) {
BLOB_CHOICE *blob_choice;
int x;
float worst = -MAX_FLOAT32;
int worst_index = -1;
float worst_near_fragment = -MAX_FLOAT32;
int worst_index_near_fragment = -1;
const CHAR_FRAGMENT **fragments = NULL;
if (chop_debug) {
if (rating_ceiling < MAX_FLOAT32)
tprintf("rating_ceiling = %8.4f\n", rating_ceiling);
else
tprintf("rating_ceiling = No Limit\n");
}
if (split_next_to_fragment && blob_choices.size() > 0) {
fragments = new const CHAR_FRAGMENT *[blob_choices.length()];
if (blob_choices[0] != NULL) {
fragments[0] = getDict().getUnicharset().get_fragment(
blob_choices[0]->unichar_id());
} else {
fragments[0] = NULL;
}
}
for (x = 0; x < blob_choices.size(); ++x) {
if (blob_choices[x] == NULL) {
if (fragments != NULL) {
delete[] fragments;
}
return x;
} else {
blob_choice = blob_choices[x];
// Populate fragments for the following position.
if (split_next_to_fragment && x+1 < blob_choices.size()) {
if (blob_choices[x + 1] != NULL) {
fragments[x + 1] = getDict().getUnicharset().get_fragment(
blob_choices[x + 1]->unichar_id());
} else {
fragments[x + 1] = NULL;
}
}
if (blob_choice->rating() < rating_ceiling &&
blob_choice->certainty() < tessedit_certainty_threshold) {
// Update worst and worst_index.
if (blob_choice->rating() > worst) {
worst_index = x;
worst = blob_choice->rating();
}
if (split_next_to_fragment) {
// Update worst_near_fragment and worst_index_near_fragment.
bool expand_following_fragment =
(x + 1 < blob_choices.size() &&
fragments[x+1] != NULL && !fragments[x+1]->is_beginning());
bool expand_preceding_fragment =
(x > 0 && fragments[x-1] != NULL && !fragments[x-1]->is_ending());
if ((expand_following_fragment || expand_preceding_fragment) &&
blob_choice->rating() > worst_near_fragment) {
worst_index_near_fragment = x;
worst_near_fragment = blob_choice->rating();
if (chop_debug) {
tprintf("worst_index_near_fragment=%d"
" expand_following_fragment=%d"
" expand_preceding_fragment=%d\n",
worst_index_near_fragment,
expand_following_fragment,
expand_preceding_fragment);
}
}
}
}
}
}
if (fragments != NULL) {
delete[] fragments;
}
// TODO(daria): maybe a threshold of badness for
// worst_near_fragment would be useful.
return worst_index_near_fragment != -1 ?
worst_index_near_fragment : worst_index;
}
void Wordrec::SegSearch(WERD_RES* word_res,
BestChoiceBundle* best_choice_bundle,
BlamerBundle* blamer_bundle) {
LMPainPoints pain_points(segsearch_max_pain_points,
segsearch_max_char_wh_ratio,
assume_fixed_pitch_char_segment,
&getDict(), segsearch_debug_level);
// Compute scaling factor that will help us recover blob outline length
// from classifier rating and certainty for the blob.
float rating_cert_scale = -1.0 * getDict().certainty_scale / rating_scale;
GenericVector<SegSearchPending> pending;
InitialSegSearch(word_res, &pain_points, &pending, best_choice_bundle,
blamer_bundle);
if (!SegSearchDone(0)) { // find a better choice
if (chop_enable && word_res->chopped_word != NULL) {
improve_by_chopping(rating_cert_scale, word_res, best_choice_bundle,
blamer_bundle, &pain_points, &pending);
}
if (chop_debug) SEAM::PrintSeams("Final seam list:", word_res->seam_array);
if (blamer_bundle != NULL &&
!blamer_bundle->ChoiceIsCorrect(word_res->best_choice)) {
blamer_bundle->SetChopperBlame(word_res, wordrec_debug_blamer);
}
}
// Keep trying to find a better path by fixing the "pain points".
MATRIX_COORD pain_point;
float pain_point_priority;
int num_futile_classifications = 0;
STRING blamer_debug;
while (wordrec_enable_assoc &&
(!SegSearchDone(num_futile_classifications) ||
(blamer_bundle != NULL &&
blamer_bundle->GuidedSegsearchStillGoing()))) {
// Get the next valid "pain point".
bool found_nothing = true;
LMPainPointsType pp_type;
while ((pp_type = pain_points.Deque(&pain_point, &pain_point_priority)) !=
LM_PPTYPE_NUM) {
if (!pain_point.Valid(*word_res->ratings)) {
word_res->ratings->IncreaseBandSize(
pain_point.row - pain_point.col + 1);
}
if (pain_point.Valid(*word_res->ratings) &&
!word_res->ratings->Classified(pain_point.col, pain_point.row,
getDict().WildcardID())) {
found_nothing = false;
break;
}
}
if (found_nothing) {
if (segsearch_debug_level > 0) tprintf("Pain points queue is empty\n");
break;
}
ProcessSegSearchPainPoint(pain_point_priority, pain_point,
LMPainPoints::PainPointDescription(pp_type),
&pending, word_res, &pain_points, blamer_bundle);
UpdateSegSearchNodes(rating_cert_scale, pain_point.col, &pending,
word_res, &pain_points, best_choice_bundle,
blamer_bundle);
if (!best_choice_bundle->updated) ++num_futile_classifications;
if (segsearch_debug_level > 0) {
tprintf("num_futile_classifications %d\n", num_futile_classifications);
}
best_choice_bundle->updated = false; // reset updated
// See if it's time to terminate SegSearch or time for starting a guided
// search for the true path to find the blame for the incorrect best_choice.
if (SegSearchDone(num_futile_classifications) &&
blamer_bundle != NULL &&
blamer_bundle->GuidedSegsearchNeeded(word_res->best_choice)) {
InitBlamerForSegSearch(word_res, &pain_points, blamer_bundle,
&blamer_debug);
}
} // end while loop exploring alternative paths
if (blamer_bundle != NULL) {
blamer_bundle->FinishSegSearch(word_res->best_choice,
wordrec_debug_blamer, &blamer_debug);
}
if (segsearch_debug_level > 0) {
tprintf("Done with SegSearch (AcceptableChoiceFound: %d)\n",
language_model_->AcceptableChoiceFound());
}
}
