#include <wordrec.h>

Inheritance diagram for tesseract::Wordrec:

Public Member Functions

Wordrec ()

virtual ~Wordrec ()

void SaveAltChoices (const LIST &best_choices, WERD_RES *word)

void FillLattice (const MATRIX &ratings, const WERD_CHOICE_LIST &best_choices, const UNICHARSET &unicharset, BlamerBundle *blamer_bundle)

void CallFillLattice (const MATRIX &ratings, const WERD_CHOICE_LIST &best_choices, const UNICHARSET &unicharset, BlamerBundle *blamer_bundle)

void SegSearch (WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)

void WordSearch (WERD_RES *word_res)

void InitialSegSearch (WERD_RES *word_res, LMPainPoints *pain_points, GenericVector< SegSearchPending > *pending, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)

void DoSegSearch (WERD_RES *word_res)

SEAM * attempt_blob_chop (TWERD *word, TBLOB *blob, inT32 blob_number, bool italic_blob, const GenericVector< SEAM * > &seams)

SEAM * chop_numbered_blob (TWERD *word, inT32 blob_number, bool italic_blob, const GenericVector< SEAM * > &seams)

SEAM * chop_overlapping_blob (const GenericVector< TBOX > &boxes, bool italic_blob, WERD_RES *word_res, int *blob_number)

void add_seam_to_queue (float new_priority, SEAM *new_seam, SeamQueue *seams)

void choose_best_seam (SeamQueue *seam_queue, const SPLIT *split, PRIORITY priority, SEAM **seam_result, TBLOB *blob, SeamPile *seam_pile)

void combine_seam (const SeamPile &seam_pile, const SEAM *seam, SeamQueue *seam_queue)

SEAM * pick_good_seam (TBLOB *blob)

void try_point_pairs (EDGEPT *points[MAX_NUM_POINTS], inT16 num_points, SeamQueue *seam_queue, SeamPile *seam_pile, SEAM **seam, TBLOB *blob)

void try_vertical_splits (EDGEPT *points[MAX_NUM_POINTS], inT16 num_points, EDGEPT_CLIST *new_points, SeamQueue *seam_queue, SeamPile *seam_pile, SEAM **seam, TBLOB *blob)

PRIORITY grade_split_length (register SPLIT *split)

PRIORITY grade_sharpness (register SPLIT *split)

bool near_point (EDGEPT *point, EDGEPT *line_pt_0, EDGEPT *line_pt_1, EDGEPT **near_pt)

virtual BLOB_CHOICE_LIST * classify_piece (const GenericVector< SEAM * > &seams, inT16 start, inT16 end, const char *description, TWERD *word, BlamerBundle *blamer_bundle)

void merge_fragments (MATRIX *ratings, inT16 num_blobs)

void get_fragment_lists (inT16 current_frag, inT16 current_row, inT16 start, inT16 num_frag_parts, inT16 num_blobs, MATRIX *ratings, BLOB_CHOICE_LIST *choice_lists)

void merge_and_put_fragment_lists (inT16 row, inT16 column, inT16 num_frag_parts, BLOB_CHOICE_LIST *choice_lists, MATRIX *ratings)

void fill_filtered_fragment_list (BLOB_CHOICE_LIST *choices, int fragment_pos, int num_frag_parts, BLOB_CHOICE_LIST *filtered_choices)

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 program_editup (const char *textbase, bool init_classifier, bool init_permute)

cc_recog

Recognize a word.

void cc_recog (WERD_RES *word)

program_editdown

This function holds any nessessary post processing for the Wise Owl program.

void program_editdown (inT32 elasped_time)

set_pass1

Get ready to do some pass 1 stuff.

void set_pass1 ()

set_pass2

Get ready to do some pass 2 stuff.

void set_pass2 ()

end_recog

Cleanup and exit the recog program.

int end_recog ()

call_matcher

Called from Tess with a blob in tess form. The blob may need rotating to the correct orientation for classification.

BLOB_CHOICE_LIST * call_matcher (TBLOB *blob)

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 dict_word (const WERD_CHOICE &word)

classify_blob

Classify the this blob if it is not already recorded in the match table. Attempt to recognize this blob as a character. The recognition rating for this blob will be stored as a part of the blob. This value will also be returned to the caller.

Parameters:

blob	Current blob
string	The string to display in ScrollView
color	The colour to use when displayed with ScrollView

BLOB_CHOICE_LIST * classify_blob (TBLOB *blob, const char *string, C_COL color, BlamerBundle *blamer_bundle)

point_priority

Assign a priority to and edge point that might be used as part of a split. The argument should be of type EDGEPT.

PRIORITY point_priority (EDGEPT *point)

add_point_to_list

Add an edge point to a POINT_GROUP containg a list of other points.

void add_point_to_list (PointHeap *point_heap, EDGEPT *point)

bool is_inside_angle (EDGEPT *pt)

angle_change

Return the change in angle (degrees) of the line segments between points one and two, and two and three.

int angle_change (EDGEPT *point1, EDGEPT *point2, EDGEPT *point3)

pick_close_point

Choose the edge point that is closest to the critical point. This point may not be exactly vertical from the critical point.

EDGEPT * pick_close_point (EDGEPT *critical_point, EDGEPT *vertical_point, int *best_dist)

prioritize_points

Find a list of edge points from the outer outline of this blob. For each of these points assign a priority. Sort these points using a heap structure so that they can be visited in order.

void prioritize_points (TESSLINE *outline, PointHeap *points)

new_min_point

Found a new minimum point try to decide whether to save it or not. Return the new value for the local minimum. If a point is saved then the local minimum is reset to NULL.

void new_min_point (EDGEPT *local_min, PointHeap *points)

new_max_point

Found a new minimum point try to decide whether to save it or not. Return the new value for the local minimum. If a point is saved then the local minimum is reset to NULL.

void new_max_point (EDGEPT *local_max, PointHeap *points)

vertical_projection_point

For one point on the outline, find the corresponding point on the other side of the outline that is a likely projection for a split point. This is done by iterating through the edge points until the X value of the point being looked at is greater than the X value of the split point. Ensure that the point being returned is not right next to the split point. Return the edge point in *best_point as a result, and any points that were newly created are also saved on the new_points list.

void vertical_projection_point (EDGEPT *split_point, EDGEPT *target_point, EDGEPT **best_point, EDGEPT_CLIST *new_points)

improve_one_blob

Finds the best place to chop, based on the worst blob, fixpt, or next to a fragment, according to the input. Returns the SEAM corresponding to the chop point, if any is found, and the index in the ratings_matrix of the chopped blob. Note that blob_choices is just a copy of the pointers in the leading diagonal of the ratings MATRIX. Although the blob is chopped, the returned SEAM is yet to be inserted into word->seam_array and the resulting blobs are unclassified, so this function can be used by ApplyBox as well as during recognition.

SEAM * improve_one_blob (const GenericVector< BLOB_CHOICE * > &blob_choices, DANGERR *fixpt, bool split_next_to_fragment, bool italic_blob, WERD_RES *word, int *blob_number)

chop_one_blob

Start with the current one-blob word and its classification. Find the worst blobs and try to divide it up to improve the ratings. Used for testing chopper.

SEAM * chop_one_blob (const GenericVector< TBOX > &boxes, const GenericVector< BLOB_CHOICE * > &blob_choices, WERD_RES *word_res, int *blob_number)

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. The results are returned in the WERD_RES.

void chop_word_main (WERD_RES *word)

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 improve_by_chopping (float rating_cert_scale, WERD_RES *word, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle, LMPainPoints *pain_points, GenericVector< SegSearchPending > *pending)

int select_blob_to_split (const GenericVector< BLOB_CHOICE * > &blob_choices, float rating_ceiling, bool split_next_to_fragment)

int select_blob_to_split_from_fixpt (DANGERR *fixpt)

Public Attributes

bool merge_fragments_in_matrix = TRUE

bool wordrec_no_block = FALSE

bool wordrec_enable_assoc = TRUE

bool force_word_assoc = FALSE

double wordrec_worst_state = 1

bool fragments_guide_chopper = FALSE

int repair_unchopped_blobs = 1

double tessedit_certainty_threshold = -2.25

int chop_debug = 0

bool chop_enable = 1

bool chop_vertical_creep = 0

int chop_split_length = 10000

int chop_same_distance = 2

int chop_min_outline_points = 6

int chop_seam_pile_size = 150

bool chop_new_seam_pile = 1

int chop_inside_angle = -50

int chop_min_outline_area = 2000

double chop_split_dist_knob = 0.5

double chop_overlap_knob = 0.9

double chop_center_knob = 0.15

int chop_centered_maxwidth = 90

double chop_sharpness_knob = 0.06

double chop_width_change_knob = 5.0

double chop_ok_split = 100.0

double chop_good_split = 50.0

int chop_x_y_weight = 3

int segment_adjust_debug = 0

bool assume_fixed_pitch_char_segment = FALSE

int wordrec_debug_level = 0

int wordrec_max_join_chunks = 4

bool wordrec_skip_no_truth_words = false

bool wordrec_debug_blamer = false

bool wordrec_run_blamer = false

int segsearch_debug_level = 0

int segsearch_max_pain_points = 2000

int segsearch_max_futile_classifications = 10

double segsearch_max_char_wh_ratio = 2.0

bool save_alt_choices = true

LanguageModel * language_model_

PRIORITY

pass2_ok_split

WERD_CHOICE * prev_word_best_choice_

GenericVector< int > blame_reasons_

void(Wordrec::* fill_lattice_ )(const MATRIX &ratings, const WERD_CHOICE_LIST &best_choices, const UNICHARSET &unicharset, BlamerBundle *blamer_bundle)

Protected Member Functions

bool SegSearchDone (int num_futile_classifications)

void UpdateSegSearchNodes (float rating_cert_scale, int starting_col, GenericVector< SegSearchPending > *pending, WERD_RES *word_res, LMPainPoints *pain_points, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)

void 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)

void ResetNGramSearch (WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, GenericVector< SegSearchPending > *pending)

void InitBlamerForSegSearch (WERD_RES *word_res, LMPainPoints *pain_points, BlamerBundle *blamer_bundle, STRING *blamer_debug)

Detailed Description

Definition at line 123 of file wordrec.h.

Constructor & Destructor Documentation

tesseract::Wordrec::Wordrec ( )

Definition at line 26 of file wordrec.cpp.

                 :
  // 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()),
  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_seam_pile_size, 150, "Max number of seams in seam_pile",
             params()),
  BOOL_MEMBER(chop_new_seam_pile, 1, "Use new seam_pile", 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()),
  INT_MEMBER(chop_centered_maxwidth, 90, "Width of (smaller) chopped blobs "
             "above which we don't care that a chop is not near the center.",
             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()),
  INT_MEMBER(wordrec_debug_level, 0,
             "Debug level for wordrec", params()),
  INT_MEMBER(wordrec_max_join_chunks, 4,
             "Max number of broken pieces to associate", params()),
  BOOL_MEMBER(wordrec_skip_no_truth_words, false,
              "Only run OCR for words that had truth recorded in BlamerBundle",
              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()),
  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, 20,
             "Maximum number of pain point classifications per chunk 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()),
  BOOL_MEMBER(save_alt_choices, true,
              "Save alternative paths found during chopping"
              " and segmentation search",
              params()) {
  prev_word_best_choice_ = NULL;
  language_model_ = new LanguageModel(&get_fontinfo_table(),
                                      &(getDict()));
  fill_lattice_ = NULL;
}

tesseract::Wordrec::~Wordrec ( ) [virtual]

Definition at line 123 of file wordrec.cpp.

                  {
  delete language_model_;
}

Member Function Documentation

void tesseract::Wordrec::add_point_to_list	(	PointHeap *	point_heap,
		EDGEPT *	point
	)

Definition at line 68 of file chop.cpp.

void tesseract::Wordrec::add_seam_to_queue	(	float	new_priority,
		SEAM *	new_seam,
		SeamQueue *	seams
	)

Definition at line 64 of file findseam.cpp.

                                                  {
  if (new_seam == NULL) return;
  if (chop_debug) {
    tprintf("Pushing new seam with priority %g :", new_priority);
    new_seam->Print("seam: ");
  }
  if (seams->size() >= MAX_NUM_SEAMS) {
    SeamPair old_pair(0, NULL);
    if (seams->PopWorst(&old_pair) && old_pair.key() <= new_priority) {
      if (chop_debug) {
        tprintf("Old seam staying with priority %g\n", old_pair.key());
      }
      delete new_seam;
      seams->Push(&old_pair);
      return;
    } else if (chop_debug) {
      tprintf("New seam with priority %g beats old worst seam with %g\n",
              new_priority, old_pair.key());
    }
  }
  SeamPair new_pair(new_priority, new_seam);
  seams->Push(&new_pair);
}

int tesseract::Wordrec::angle_change	(	EDGEPT *	point1,
		EDGEPT *	point2,
		EDGEPT *	point3
	)

Definition at line 92 of file chop.cpp.

SEAM * tesseract::Wordrec::attempt_blob_chop	(	TWERD *	word,
		TBLOB *	blob,
		inT32	blob_number,
		bool	italic_blob,
		const GenericVector< SEAM * > &	seams
	)

Definition at line 170 of file chopper.cpp.

                                                                    {
  if (repair_unchopped_blobs)
    preserve_outline_tree (blob->outlines);
  TBLOB *other_blob = TBLOB::ShallowCopy(*blob);       /* Make new blob */
  // Insert it into the word.
  word->blobs.insert(other_blob, blob_number + 1);

  SEAM *seam = NULL;
  if (prioritize_division) {
    TPOINT location;
    if (divisible_blob(blob, italic_blob, &location)) {
      seam = new SEAM(0.0f, location);
    }
  }
  if (seam == NULL)
    seam = pick_good_seam(blob);
  if (chop_debug) {
    if (seam != NULL)
      seam->Print("Good seam picked=");
    else
      tprintf("\n** no seam picked *** \n");
  }
  if (seam) {
    seam->ApplySeam(italic_blob, blob, other_blob);
  }

  seam = CheckSeam(chop_debug, blob_number, word, blob, other_blob,
                   seams, seam);
  if (seam == NULL) {
    if (repair_unchopped_blobs)
      restore_outline_tree(blob->outlines);
    if (allow_blob_division && !prioritize_division) {
      // If the blob can simply be divided into outlines, then do that.
      TPOINT location;
      if (divisible_blob(blob, italic_blob, &location)) {
        other_blob = TBLOB::ShallowCopy(*blob);       /* Make new blob */
        word->blobs.insert(other_blob, blob_number + 1);
        seam = new SEAM(0.0f, location);
        seam->ApplySeam(italic_blob, blob, other_blob);
        seam = CheckSeam(chop_debug, blob_number, word, blob, other_blob,
                         seams, seam);
      }
    }
  }
  if (seam != NULL) {
    // Make sure this seam doesn't get chopped again.
    seam->Finalize();
  }
  return seam;
}

BLOB_CHOICE_LIST * tesseract::Wordrec::call_matcher ( TBLOB * blob )

Definition at line 134 of file tface.cpp.

                                                       {
  // Rotate the blob for classification if necessary.
  TBLOB* rotated_blob = tessblob->ClassifyNormalizeIfNeeded();
  if (rotated_blob == NULL) {
    rotated_blob = tessblob;
  }
  BLOB_CHOICE_LIST *ratings = new BLOB_CHOICE_LIST();  // matcher result
  AdaptiveClassifier(rotated_blob, ratings);
  if (rotated_blob != tessblob) {
    delete rotated_blob;
  }
  return ratings;
}

void tesseract::Wordrec::CallFillLattice	(	const MATRIX &	ratings,
		const WERD_CHOICE_LIST &	best_choices,
		const UNICHARSET &	unicharset,
		BlamerBundle *	blamer_bundle
	)		`[inline]`

Definition at line 195 of file wordrec.h.

                                                    {
    (this->*fill_lattice_)(ratings, best_choices, unicharset, blamer_bundle);
  }

void tesseract::Wordrec::cc_recog ( WERD_RES * word )

Definition at line 109 of file tface.cpp.

                                     {
  getDict().reset_hyphen_vars(word->word->flag(W_EOL));
  chop_word_main(word);
  word->DebugWordChoices(getDict().stopper_debug_level >= 1,
                         getDict().word_to_debug.string());
  ASSERT_HOST(word->StatesAllValid());
}

void tesseract::Wordrec::choose_best_seam	(	SeamQueue *	seam_queue,
		const SPLIT *	split,
		PRIORITY	priority,
		SEAM **	seam_result,
		TBLOB *	blob,
		SeamPile *	seam_pile
	)

Definition at line 103 of file findseam.cpp.

                                                                 {
  SEAM *seam;
  char str[80];
  float my_priority;
  /* Add seam of split */
  my_priority = priority;
  if (split != NULL) {
    TPOINT split_point = split->point1->pos;
    split_point += split->point2->pos;
    split_point /= 2;
    seam = new SEAM(my_priority, split_point, *split);
    if (chop_debug > 1) seam->Print("Partial priority    ");
    add_seam_to_queue(my_priority, seam, seam_queue);

    if (my_priority > chop_good_split)
      return;
  }

  TBOX bbox = blob->bounding_box();
  /* Queue loop */
  while (!seam_queue->empty()) {
    SeamPair seam_pair;
    seam_queue->Pop(&seam_pair);
    seam = seam_pair.extract_data();
    /* Set full priority */
    my_priority = seam->FullPriority(bbox.left(), bbox.right(),
                                     chop_overlap_knob, chop_centered_maxwidth,
                                     chop_center_knob, chop_width_change_knob);
    if (chop_debug) {
      sprintf (str, "Full my_priority %0.0f,  ", my_priority);
      seam->Print(str);
    }

    if ((*seam_result == NULL || (*seam_result)->priority() > my_priority) &&
        my_priority < chop_ok_split) {
      /* No crossing */
      if (seam->IsHealthy(*blob, chop_min_outline_points,
                          chop_min_outline_area)) {
        delete *seam_result;
        *seam_result = new SEAM(*seam);
        (*seam_result)->set_priority(my_priority);
      } else {
        delete seam;
        seam = NULL;
        my_priority = BAD_PRIORITY;
      }
    }

    if (my_priority < chop_good_split) {
      if (seam)
        delete seam;
      return;                    /* Made good answer */
    }

    if (seam) {
      /* Combine with others */
      if (seam_pile->size() < chop_seam_pile_size) {
        combine_seam(*seam_pile, seam, seam_queue);
        SeamDecPair pair(seam_pair.key(), seam);
        seam_pile->Push(&pair);
      } else if (chop_new_seam_pile &&
                 seam_pile->size() == chop_seam_pile_size &&
                 seam_pile->PeekTop().key() > seam_pair.key()) {
        combine_seam(*seam_pile, seam, seam_queue);
        SeamDecPair pair;
        seam_pile->Pop(&pair);  // pop the worst.
        // Replace the seam in pair (deleting the old one) with
        // the new seam and score, then push back into the heap.
        pair.set_key(seam_pair.key());
        pair.set_data(seam);
        seam_pile->Push(&pair);
      } else {
        delete seam;
      }
    }

    my_priority = seam_queue->empty() ? NO_FULL_PRIORITY
                                      : seam_queue->PeekTop().key();
    if ((my_priority > chop_ok_split) ||
      (my_priority > chop_good_split && split))
      return;
  }
}

SEAM * tesseract::Wordrec::chop_numbered_blob	(	TWERD *	word,
		inT32	blob_number,
		bool	italic_blob,
		const GenericVector< SEAM * > &	seams
	)

Definition at line 224 of file chopper.cpp.

                                                                     {
  return attempt_blob_chop(word, word->blobs[blob_number], blob_number,
                           italic_blob, seams);
}

SEAM * tesseract::Wordrec::chop_one_blob	(	const GenericVector< TBOX > &	boxes,
		const GenericVector< BLOB_CHOICE * > &	blob_choices,
		WERD_RES *	word_res,
		int *	blob_number
	)

Definition at line 374 of file chopper.cpp.

                                               {
  if (prioritize_division) {
    return chop_overlapping_blob(boxes, true, word_res, blob_number);
  } else {
    return improve_one_blob(blob_choices, NULL, false, true, word_res,
                            blob_number);
  }
}

SEAM * tesseract::Wordrec::chop_overlapping_blob	(	const GenericVector< TBOX > &	boxes,
		bool	italic_blob,
		WERD_RES *	word_res,
		int *	blob_number
	)

Definition at line 232 of file chopper.cpp.

                                                       {
  TWERD *word = word_res->chopped_word;
  for (*blob_number = 0; *blob_number < word->NumBlobs(); ++*blob_number) {
    TBLOB *blob = word->blobs[*blob_number];
    TPOINT topleft, botright;
    topleft.x = blob->bounding_box().left();
    topleft.y = blob->bounding_box().top();
    botright.x = blob->bounding_box().right();
    botright.y = blob->bounding_box().bottom();

    TPOINT original_topleft, original_botright;
    word_res->denorm.DenormTransform(NULL, topleft, &original_topleft);
    word_res->denorm.DenormTransform(NULL, botright, &original_botright);

    TBOX original_box = TBOX(original_topleft.x, original_botright.y,
                             original_botright.x, original_topleft.y);

    bool almost_equal_box = false;
    int num_overlap = 0;
    for (int i = 0; i < boxes.size(); i++) {
      if (original_box.overlap_fraction(boxes[i]) > 0.125)
        num_overlap++;
      if (original_box.almost_equal(boxes[i], 3))
        almost_equal_box = true;
    }

    TPOINT location;
    if (divisible_blob(blob, italic_blob, &location) ||
        (!almost_equal_box && num_overlap > 1)) {
      SEAM *seam = attempt_blob_chop(word, blob, *blob_number,
                                     italic_blob, word_res->seam_array);
      if (seam != NULL)
        return seam;
    }
  }

  *blob_number = -1;
  return NULL;
}

void tesseract::Wordrec::chop_word_main ( WERD_RES * word )

Definition at line 394 of file chopper.cpp.

                                           {
  int num_blobs = word->chopped_word->NumBlobs();
  if (word->ratings == NULL) {
    word->ratings = new MATRIX(num_blobs, wordrec_max_join_chunks);
  }
  if (word->ratings->get(0, 0) == NULL) {
    // Run initial classification.
    for (int b = 0; b < num_blobs; ++b) {
      BLOB_CHOICE_LIST* choices = classify_piece(word->seam_array, b, b,
                                                 "Initial:", word->chopped_word,
                                                 word->blamer_bundle);
      word->ratings->put(b, b, choices);
    }
  } else {
    // Blobs have been pre-classified. Set matrix cell for all blob choices
    for (int col = 0; col < word->ratings->dimension(); ++col) {
      for (int row = col; row < word->ratings->dimension() &&
           row < col + word->ratings->bandwidth(); ++row) {
        BLOB_CHOICE_LIST* choices = word->ratings->get(col, row);
        if (choices != NULL) {
          BLOB_CHOICE_IT bc_it(choices);
          for (bc_it.mark_cycle_pt(); !bc_it.cycled_list(); bc_it.forward()) {
            bc_it.data()->set_matrix_cell(col, row);
          }
        }
      }
    }
  }

  // Run Segmentation Search.
  BestChoiceBundle best_choice_bundle(word->ratings->dimension());
  SegSearch(word, &best_choice_bundle, word->blamer_bundle);

  if (word->best_choice == NULL) {
    // SegSearch found no valid paths, so just use the leading diagonal.
    word->FakeWordFromRatings();
  }
  word->RebuildBestState();
  // If we finished without a hyphen at the end of the word, let the next word
  // be found in the dictionary.
  if (word->word->flag(W_EOL) &&
      !getDict().has_hyphen_end(*word->best_choice)) {
    getDict().reset_hyphen_vars(true);
  }

  if (word->blamer_bundle != NULL && this->fill_lattice_ != NULL) {
    CallFillLattice(*word->ratings, word->best_choices,
                    *word->uch_set, word->blamer_bundle);
  }
  if (wordrec_debug_level > 0) {
    tprintf("Final Ratings Matrix:\n");
    word->ratings->print(getDict().getUnicharset());
  }
  word->FilterWordChoices(getDict().stopper_debug_level);
}

BLOB_CHOICE_LIST * tesseract::Wordrec::classify_blob	(	TBLOB *	blob,
		const char *	string,
		C_COL	color,
		BlamerBundle *	blamer_bundle
	)

Definition at line 56 of file wordclass.cpp.

                                                                      {
#ifndef GRAPHICS_DISABLED
  if (wordrec_display_all_blobs)
    display_blob(blob, color);
#endif
  // TODO(rays) collapse with call_matcher and move all to wordrec.cpp.
  BLOB_CHOICE_LIST* choices = call_matcher(blob);
  // If a blob with the same bounding box as one of the truth character
  // bounding boxes is not classified as the corresponding truth character
  // blame character classifier for incorrect answer.
  if (blamer_bundle != NULL) {
    blamer_bundle->BlameClassifier(getDict().getUnicharset(),
                                   blob->bounding_box(),
                                   *choices,
                                   wordrec_debug_blamer);
  }
  #ifndef GRAPHICS_DISABLED
  if (classify_debug_level && string)
    print_ratings_list(string, choices, getDict().getUnicharset());

  if (wordrec_blob_pause)
    window_wait(blob_window);
#endif

  return choices;
}

BLOB_CHOICE_LIST * tesseract::Wordrec::classify_piece	(	const GenericVector< SEAM * > &	seams,
		inT16	start,
		inT16	end,
		const char *	description,
		TWERD *	word,
		BlamerBundle *	blamer_bundle
	)		`[virtual]`

Definition at line 57 of file pieces.cpp.

                                                                       {
  if (end > start) SEAM::JoinPieces(seams, word->blobs, start, end);
  BLOB_CHOICE_LIST *choices = classify_blob(word->blobs[start], description,
                                            White, blamer_bundle);
  // Set the matrix_cell_ entries in all the BLOB_CHOICES.
  BLOB_CHOICE_IT bc_it(choices);
  for (bc_it.mark_cycle_pt(); !bc_it.cycled_list(); bc_it.forward()) {
    bc_it.data()->set_matrix_cell(start, end);
  }

  if (end > start) SEAM::BreakPieces(seams, word->blobs, start, end);

  return (choices);
}

void tesseract::Wordrec::combine_seam	(	const SeamPile &	seam_pile,
		const SEAM *	seam,
		SeamQueue *	seam_queue
	)

Definition at line 197 of file findseam.cpp.

                                                                    {
  for (int x = 0; x < seam_pile.size(); ++x) {
    const SEAM *this_one = seam_pile.get(x).data();
    if (seam->CombineableWith(*this_one, SPLIT_CLOSENESS, chop_ok_split)) {
      SEAM *new_one = new SEAM(*seam);
      new_one->CombineWith(*this_one);
      if (chop_debug > 1) new_one->Print("Combo priority       ");
      add_seam_to_queue(new_one->priority(), new_one, seam_queue);
    }
  }
}

int tesseract::Wordrec::dict_word ( const WERD_CHOICE & word )

Definition at line 124 of file tface.cpp.

                                              {
  return getDict().valid_word(word);
}

void tesseract::Wordrec::DoSegSearch ( WERD_RES * word_res )

Definition at line 31 of file segsearch.cpp.

                                            {
  BestChoiceBundle best_choice_bundle(word_res->ratings->dimension());
  // Run Segmentation Search.
  SegSearch(word_res, &best_choice_bundle, NULL);
}

int tesseract::Wordrec::end_recog ( )

Definition at line 61 of file tface.cpp.

                       {
  program_editdown (0);

  return (0);
}

void tesseract::Wordrec::fill_filtered_fragment_list	(	BLOB_CHOICE_LIST *	choices,
		int	fragment_pos,
		int	num_frag_parts,
		BLOB_CHOICE_LIST *	filtered_choices
	)

Definition at line 106 of file pieces.cpp.

                                                                              {
  BLOB_CHOICE_IT filtered_choices_it(filtered_choices);
  BLOB_CHOICE_IT choices_it(choices);

  for (choices_it.mark_cycle_pt(); !choices_it.cycled_list();
       choices_it.forward()) {
    UNICHAR_ID choice_unichar_id = choices_it.data()->unichar_id();
    const CHAR_FRAGMENT *frag = unicharset.get_fragment(choice_unichar_id);

    if (frag != NULL && frag->get_pos() == fragment_pos &&
        frag->get_total() == num_frag_parts) {
      // Recover the unichar_id of the unichar that this fragment is
      // a part of
      BLOB_CHOICE *b = new BLOB_CHOICE(*choices_it.data());
      int original_unichar = unicharset.unichar_to_id(frag->get_unichar());
      b->set_unichar_id(original_unichar);
      filtered_choices_it.add_to_end(b);
    }
  }

  filtered_choices->sort(SortByUnicharID<BLOB_CHOICE>);
}

void tesseract::Wordrec::FillLattice	(	const MATRIX &	ratings,
		const WERD_CHOICE_LIST &	best_choices,
		const UNICHARSET &	unicharset,
		BlamerBundle *	blamer_bundle
	)

void tesseract::Wordrec::get_fragment_lists	(	inT16	current_frag,
		inT16	current_row,
		inT16	start,
		inT16	num_frag_parts,
		inT16	num_blobs,
		MATRIX *	ratings,
		BLOB_CHOICE_LIST *	choice_lists
	)

Definition at line 283 of file pieces.cpp.

                                                                 {
  if (current_frag == num_frag_parts) {
    merge_and_put_fragment_lists(start, current_row - 1, num_frag_parts,
                                 choice_lists, ratings);
    return;
  }

  for (inT16 x = current_row; x < num_blobs; x++) {
    BLOB_CHOICE_LIST *choices = ratings->get(current_row, x);
    if (choices == NULL)
      continue;

    fill_filtered_fragment_list(choices, current_frag, num_frag_parts,
                                &choice_lists[current_frag]);
    if (!choice_lists[current_frag].empty()) {
      get_fragment_lists(current_frag + 1, x + 1, start, num_frag_parts,
                         num_blobs, ratings, choice_lists);
      choice_lists[current_frag].clear();
    }
  }
}

PRIORITY tesseract::Wordrec::grade_sharpness ( register SPLIT * split )

Definition at line 74 of file gradechop.cpp.

                                                       {
  PRIORITY grade;

  grade = point_priority (split->point1) + point_priority (split->point2);

  if (grade < -360.0)
    grade = 0;
  else
    grade += 360.0;

  grade *= chop_sharpness_knob;       /* Values 0 to -360 */

  return (grade);
}

PRIORITY tesseract::Wordrec::grade_split_length ( register SPLIT * split )

Definition at line 51 of file gradechop.cpp.

                                                          {
  PRIORITY grade;
  float split_length;

  split_length =
      split->point1->WeightedDistance(*split->point2, chop_x_y_weight);

  if (split_length <= 0)
    grade = 0;
  else
    grade = sqrt (split_length) * chop_split_dist_knob;

  return (MAX (0.0, grade));
}

void tesseract::Wordrec::improve_by_chopping	(	float	rating_cert_scale,
		WERD_RES *	word,
		BestChoiceBundle *	best_choice_bundle,
		BlamerBundle *	blamer_bundle,
		LMPainPoints *	pain_points,
		GenericVector< SegSearchPending > *	pending
	)

Definition at line 457 of file chopper.cpp.

                                                                            {
  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);
  }
}

SEAM * tesseract::Wordrec::improve_one_blob	(	const GenericVector< BLOB_CHOICE * > &	blob_choices,
		DANGERR *	fixpt,
		bool	split_next_to_fragment,
		bool	italic_blob,
		WERD_RES *	word,
		int *	blob_number
	)

Definition at line 330 of file chopper.cpp.

                                                  {
  float rating_ceiling = MAX_FLOAT32;
  SEAM *seam = NULL;
  do {
    *blob_number = select_blob_to_split_from_fixpt(fixpt);
    if (chop_debug) tprintf("blob_number from fixpt = %d\n", *blob_number);
    bool split_point_from_dict = (*blob_number != -1);
    if (split_point_from_dict) {
      fixpt->clear();
    } else {
      *blob_number = select_blob_to_split(blob_choices, rating_ceiling,
                                          split_next_to_fragment);
    }
    if (chop_debug) tprintf("blob_number = %d\n", *blob_number);
    if (*blob_number == -1)
      return NULL;

    // TODO(rays) it may eventually help to allow italic_blob to be true,
    seam = chop_numbered_blob(word->chopped_word, *blob_number, italic_blob,
                              word->seam_array);
    if (seam != NULL)
      return seam;  // Success!
    if (blob_choices[*blob_number] == NULL)
      return NULL;
    if (!split_point_from_dict) {
      // We chopped the worst rated blob, try something else next time.
      rating_ceiling = blob_choices[*blob_number]->rating();
    }
  } while (true);
  return seam;
}

void tesseract::Wordrec::InitBlamerForSegSearch	(	WERD_RES *	word_res,
		LMPainPoints *	pain_points,
		BlamerBundle *	blamer_bundle,
		STRING *	blamer_debug
	)		`[protected]`

Definition at line 342 of file segsearch.cpp.

                                                           {
  pain_points->Clear();  // Clear pain points heap.
  TessResultCallback2<bool, int, int>* pp_cb = NewPermanentTessCallback(
      pain_points, &LMPainPoints::GenerateForBlamer,
      static_cast<double>(segsearch_max_char_wh_ratio), word_res);
  blamer_bundle->InitForSegSearch(word_res->best_choice, word_res->ratings,
                                  getDict().WildcardID(), wordrec_debug_blamer,
                                  blamer_debug, pp_cb);
  delete pp_cb;
}

void tesseract::Wordrec::InitialSegSearch	(	WERD_RES *	word_res,
		LMPainPoints *	pain_points,
		GenericVector< SegSearchPending > *	pending,
		BestChoiceBundle *	best_choice_bundle,
		BlamerBundle *	blamer_bundle
	)

Definition at line 150 of file segsearch.cpp.

                                                            {
  if (segsearch_debug_level > 0) {
    tprintf("Starting SegSearch on ratings matrix%s:\n",
            wordrec_enable_assoc ? " (with assoc)" : "");
    word_res->ratings->print(getDict().getUnicharset());
  }

  pain_points->GenerateInitial(word_res);

  // 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;

  language_model_->InitForWord(prev_word_best_choice_,
                               assume_fixed_pitch_char_segment,
                               segsearch_max_char_wh_ratio, rating_cert_scale);

  // Initialize blamer-related information: map character boxes recorded in
  // blamer_bundle->norm_truth_word to the corresponding i,j indices in the
  // ratings matrix. We expect this step to succeed, since when running the
  // chopper we checked that the correct chops are present.
  if (blamer_bundle != NULL) {
    blamer_bundle->SetupCorrectSegmentation(word_res->chopped_word,
                                            wordrec_debug_blamer);
  }

  // pending[col] tells whether there is update work to do to combine
  // best_choice_bundle->beam[col - 1] with some BLOB_CHOICEs in matrix[col, *].
  // As the language model state is updated, pending entries are modified to
  // minimize duplication of work. It is important that during the update the
  // children are considered in the non-decreasing order of their column, since
  // this guarantees that all the parents would be up to date before an update
  // of a child is done.
  pending->init_to_size(word_res->ratings->dimension(), SegSearchPending());

  // Search the ratings matrix for the initial best path.
  (*pending)[0].SetColumnClassified();
  UpdateSegSearchNodes(rating_cert_scale, 0, pending, word_res,
                       pain_points, best_choice_bundle, blamer_bundle);
}

bool tesseract::Wordrec::is_inside_angle ( EDGEPT * pt )

Definition at line 82 of file chop.cpp.

void tesseract::Wordrec::merge_and_put_fragment_lists	(	inT16	row,
		inT16	column,
		inT16	num_frag_parts,
		BLOB_CHOICE_LIST *	choice_lists,
		MATRIX *	ratings
	)

Definition at line 139 of file pieces.cpp.

                                                            {
  BLOB_CHOICE_IT *choice_lists_it = new BLOB_CHOICE_IT[num_frag_parts];

  for (int i = 0; i < num_frag_parts; i++) {
    choice_lists_it[i].set_to_list(&choice_lists[i]);
    choice_lists_it[i].mark_cycle_pt();
  }

  BLOB_CHOICE_LIST *merged_choice = ratings->get(row, column);
  if (merged_choice == NULL)
    merged_choice = new BLOB_CHOICE_LIST;

  bool end_of_list = false;
  BLOB_CHOICE_IT merged_choice_it(merged_choice);
  while (!end_of_list) {
    // Find the maximum unichar_id of the current entry the iterators
    // are pointing at
    UNICHAR_ID max_unichar_id = choice_lists_it[0].data()->unichar_id();
    for (int i = 0; i < num_frag_parts; i++) {
      UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
      if (max_unichar_id < unichar_id) {
        max_unichar_id = unichar_id;
      }
    }

    // Move the each iterators until it gets to an entry that has a
    // value greater than or equal to max_unichar_id
    for (int i = 0; i < num_frag_parts; i++) {
      UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
      while (!choice_lists_it[i].cycled_list() &&
             unichar_id < max_unichar_id) {
        choice_lists_it[i].forward();
        unichar_id = choice_lists_it[i].data()->unichar_id();
      }
      if (choice_lists_it[i].cycled_list()) {
        end_of_list = true;
        break;
      }
    }

    if (end_of_list)
      break;

    // Checks if the fragments are parts of the same character
    UNICHAR_ID first_unichar_id = choice_lists_it[0].data()->unichar_id();
    bool same_unichar = true;
    for (int i = 1; i < num_frag_parts; i++) {
      UNICHAR_ID unichar_id = choice_lists_it[i].data()->unichar_id();
      if (unichar_id != first_unichar_id) {
        same_unichar = false;
        break;
      }
    }

    if (same_unichar) {
      // Add the merged character to the result
      UNICHAR_ID merged_unichar_id = first_unichar_id;
      GenericVector<ScoredFont> merged_fonts =
          choice_lists_it[0].data()->fonts();
      float merged_min_xheight = choice_lists_it[0].data()->min_xheight();
      float merged_max_xheight = choice_lists_it[0].data()->max_xheight();
      float positive_yshift = 0, negative_yshift = 0;
      int merged_script_id = choice_lists_it[0].data()->script_id();
      BlobChoiceClassifier classifier = choice_lists_it[0].data()->classifier();

      float merged_rating = 0, merged_certainty = 0;
      for (int i = 0; i < num_frag_parts; i++) {
        float rating = choice_lists_it[i].data()->rating();
        float certainty = choice_lists_it[i].data()->certainty();

        if (i == 0 || certainty < merged_certainty)
          merged_certainty = certainty;
        merged_rating += rating;

        choice_lists_it[i].forward();
        if (choice_lists_it[i].cycled_list())
          end_of_list = true;
        IntersectRange(choice_lists_it[i].data()->min_xheight(),
                       choice_lists_it[i].data()->max_xheight(),
                       &merged_min_xheight, &merged_max_xheight);
        float yshift = choice_lists_it[i].data()->yshift();
        if (yshift > positive_yshift) positive_yshift = yshift;
        if (yshift < negative_yshift) negative_yshift = yshift;
        // Use the min font rating over the parts.
        // TODO(rays) font lists are unsorted. Need to be faster?
        const GenericVector<ScoredFont>& frag_fonts =
            choice_lists_it[i].data()->fonts();
        for (int f = 0; f < frag_fonts.size(); ++f) {
          int merged_f = 0;
          for (merged_f = 0; merged_f < merged_fonts.size() &&
               merged_fonts[merged_f].fontinfo_id != frag_fonts[f].fontinfo_id;
               ++merged_f) {}
          if (merged_f == merged_fonts.size()) {
            merged_fonts.push_back(frag_fonts[f]);
          } else if (merged_fonts[merged_f].score > frag_fonts[f].score) {
            merged_fonts[merged_f].score = frag_fonts[f].score;
          }
        }
      }

      float merged_yshift = positive_yshift != 0
          ? (negative_yshift != 0 ? 0 : positive_yshift)
          : negative_yshift;
      BLOB_CHOICE* choice = new BLOB_CHOICE(merged_unichar_id,
                                            merged_rating,
                                            merged_certainty,
                                            merged_script_id,
                                            merged_min_xheight,
                                            merged_max_xheight,
                                            merged_yshift,
                                            classifier);
      choice->set_fonts(merged_fonts);
      merged_choice_it.add_to_end(choice);
    }
  }

  if (classify_debug_level)
    print_ratings_list("Merged Fragments", merged_choice,
                       unicharset);

  if (merged_choice->empty())
    delete merged_choice;
  else
    ratings->put(row, column, merged_choice);

  delete [] choice_lists_it;
}

void tesseract::Wordrec::merge_fragments	(	MATRIX *	ratings,
		inT16	num_blobs
	)

Definition at line 315 of file pieces.cpp.

                                                              {
  BLOB_CHOICE_LIST choice_lists[CHAR_FRAGMENT::kMaxChunks];
  for (inT16 start = 0; start < num_blobs; start++) {
    for (int frag_parts = 2; frag_parts <= CHAR_FRAGMENT::kMaxChunks;
         frag_parts++) {
      get_fragment_lists(0, start, start, frag_parts, num_blobs,
                         ratings, choice_lists);
    }
  }

  // Delete fragments from the rating matrix
  for (inT16 x = 0; x < num_blobs; x++) {
    for (inT16 y = x; y < num_blobs; y++) {
      BLOB_CHOICE_LIST *choices = ratings->get(x, y);
      if (choices != NULL) {
        BLOB_CHOICE_IT choices_it(choices);
        for (choices_it.mark_cycle_pt(); !choices_it.cycled_list();
             choices_it.forward()) {
          UNICHAR_ID choice_unichar_id = choices_it.data()->unichar_id();
          const CHAR_FRAGMENT *frag =
              unicharset.get_fragment(choice_unichar_id);
          if (frag != NULL)
            delete choices_it.extract();
        }
      }
    }
  }
}

bool tesseract::Wordrec::near_point	(	EDGEPT *	point,
		EDGEPT *	line_pt_0,
		EDGEPT *	line_pt_1,
		EDGEPT **	near_pt
	)

Definition at line 49 of file outlines.cpp.

                                           {
  TPOINT p;

  float slope;
  float intercept;

  float x0 = line_pt_0->pos.x;
  float x1 = line_pt_1->pos.x;
  float y0 = line_pt_0->pos.y;
  float y1 = line_pt_1->pos.y;

  if (x0 == x1) {
                                 /* Handle vertical line */
    p.x = (inT16) x0;
    p.y = point->pos.y;
  }
  else {
    /* Slope and intercept */
    slope = (y0 - y1) / (x0 - x1);
    intercept = y1 - x1 * slope;

    /* Find perpendicular */
    p.x = (inT16) ((point->pos.x + (point->pos.y - intercept) * slope) /
      (slope * slope + 1));
    p.y = (inT16) (slope * p.x + intercept);
  }

  if (is_on_line (p, line_pt_0->pos, line_pt_1->pos) &&
    (!same_point (p, line_pt_0->pos)) && (!same_point (p, line_pt_1->pos))) {
    /* Intersection on line */
    *near_pt = make_edgept(p.x, p.y, line_pt_1, line_pt_0);
    return true;
  } else {                           /* Intersection not on line */
    *near_pt = closest(point, line_pt_0, line_pt_1);
    return false;
  }
}

void tesseract::Wordrec::new_max_point	(	EDGEPT *	local_max,
		PointHeap *	points
	)

Definition at line 249 of file chop.cpp.

               {
    add_point_to_list(points, local_max);
    return;
  }

  if (dir == 0 && point_priority (local_max) < 0) {
    add_point_to_list(points, local_max);
    return;
  }
}

void tesseract::Wordrec::new_min_point	(	EDGEPT *	local_min,
		PointHeap *	points
	)

Definition at line 225 of file chop.cpp.

               {
    add_point_to_list(points, local_min);
    return;
  }

  if (dir == 0 && point_priority (local_min) < 0) {
    add_point_to_list(points, local_min);
    return;
  }
}

EDGEPT * tesseract::Wordrec::pick_close_point	(	EDGEPT *	critical_point,
		EDGEPT *	vertical_point,
		int *	best_dist
	)

Definition at line 128 of file chop.cpp.

     {
    found_better = FALSE;

    this_distance = edgept_dist (critical_point, vertical_point);
    if (this_distance <= *best_dist) {

      if (!(same_point (critical_point->pos, vertical_point->pos) ||
        same_point (critical_point->pos, vertical_point->next->pos) ||
        (best_point && same_point (best_point->pos, vertical_point->pos)) ||
      is_exterior_point (critical_point, vertical_point))) {
        *best_dist = this_distance;
        best_point = vertical_point;
        if (chop_vertical_creep)
          found_better = TRUE;
      }
    }
    vertical_point = vertical_point->next;
  }
  while (found_better == TRUE);

  return (best_point);
}

SEAM * tesseract::Wordrec::pick_good_seam ( TBLOB * blob )

Definition at line 216 of file findseam.cpp.

                                         {
  SeamPile seam_pile(chop_seam_pile_size);
  EDGEPT *points[MAX_NUM_POINTS];
  EDGEPT_CLIST new_points;
  SEAM *seam = NULL;
  TESSLINE *outline;
  inT16 num_points = 0;

#ifndef GRAPHICS_DISABLED
  if (chop_debug > 2)
    wordrec_display_splits.set_value(true);

  draw_blob_edges(blob);
#endif

  PointHeap point_heap(MAX_NUM_POINTS);
  for (outline = blob->outlines; outline; outline = outline->next)
    prioritize_points(outline, &point_heap);

  while (!point_heap.empty() && num_points < MAX_NUM_POINTS) {
    points[num_points++] = point_heap.PeekTop().data;
    point_heap.Pop(NULL);
  }

  /* Initialize queue */
  SeamQueue seam_queue(MAX_NUM_SEAMS);

  try_point_pairs(points, num_points, &seam_queue, &seam_pile, &seam, blob);
  try_vertical_splits(points, num_points, &new_points,
                      &seam_queue, &seam_pile, &seam, blob);

  if (seam == NULL) {
    choose_best_seam(&seam_queue, NULL, BAD_PRIORITY, &seam, blob, &seam_pile);
  } else if (seam->priority() > chop_good_split) {
    choose_best_seam(&seam_queue, NULL, seam->priority(), &seam, blob,
                     &seam_pile);
  }

  EDGEPT_C_IT it(&new_points);
  for (it.mark_cycle_pt(); !it.cycled_list(); it.forward()) {
    EDGEPT *inserted_point = it.data();
    if (seam == NULL || !seam->UsesPoint(inserted_point)) {
      for (outline = blob->outlines; outline; outline = outline->next) {
        if (outline->loop == inserted_point) {
          outline->loop = outline->loop->next;
        }
      }
      remove_edgept(inserted_point);
    }
  }

  if (seam) {
    if (seam->priority() > chop_ok_split) {
      delete seam;
      seam = NULL;
    }
#ifndef GRAPHICS_DISABLED
    else if (wordrec_display_splits) {
      seam->Mark(edge_window);
      if (chop_debug > 2) {
        update_edge_window();
        edge_window_wait();
      }
    }
#endif
  }

  if (chop_debug)
    wordrec_display_splits.set_value(false);

  return (seam);
}

PRIORITY tesseract::Wordrec::point_priority ( EDGEPT * point )

Definition at line 58 of file chop.cpp.

void tesseract::Wordrec::prioritize_points	(	TESSLINE *	outline,
		PointHeap *	points
	)

Definition at line 166 of file chop.cpp.

     {
    if (this_point->vec.y < 0) {
                                 /* Look for minima */
      if (local_max != NULL)
        new_max_point(local_max, points);
      else if (is_inside_angle (this_point))
        add_point_to_list(points, this_point);
      local_max = NULL;
      local_min = this_point->next;
    }
    else if (this_point->vec.y > 0) {
                                 /* Look for maxima */
      if (local_min != NULL)
        new_min_point(local_min, points);
      else if (is_inside_angle (this_point))
        add_point_to_list(points, this_point);
      local_min = NULL;
      local_max = this_point->next;
    }
    else {
      /* Flat area */
      if (local_max != NULL) {
        if (local_max->prev->vec.y != 0) {
          new_max_point(local_max, points);
        }
        local_max = this_point->next;
        local_min = NULL;
      }
      else {
        if (local_min->prev->vec.y != 0) {
          new_min_point(local_min, points);
        }
        local_min = this_point->next;
        local_max = NULL;
      }
    }

                                 /* Next point */
    this_point = this_point->next;
  }
  while (this_point != outline->loop);
}

void tesseract::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
	)		`[protected]`

Definition at line 262 of file segsearch.cpp.

                                                            {
  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);
}

void tesseract::Wordrec::program_editdown ( inT32 elasped_time )

Definition at line 74 of file tface.cpp.

                                                 {
  EndAdaptiveClassifier();
  getDict().End();
}

void tesseract::Wordrec::program_editup	(	const char *	textbase,
		bool	init_classifier,
		bool	init_permute
	)

Definition at line 46 of file tface.cpp.

                                             {
  if (textbase != NULL) imagefile = textbase;
  InitFeatureDefs(&feature_defs_);
  InitAdaptiveClassifier(init_classifier);
  if (init_dict) getDict().Load(Dict::GlobalDawgCache());
  pass2_ok_split = chop_ok_split;
}

void tesseract::Wordrec::ResetNGramSearch	(	WERD_RES *	word_res,
		BestChoiceBundle *	best_choice_bundle,
		GenericVector< SegSearchPending > *	pending
	)		`[protected]`

Definition at line 325 of file segsearch.cpp.

                                                                         {
  // TODO(rays) More refactoring required here.
  // Delete existing viterbi states.
  for (int col = 0; col < best_choice_bundle->beam.size(); ++col) {
    best_choice_bundle->beam[col]->Clear();
  }
  // Reset best_choice_bundle.
  word_res->ClearWordChoices();
  best_choice_bundle->best_vse = NULL;
  // Clear out all existing pendings and add a new one for the first column.
  (*pending)[0].SetColumnClassified();
  for (int i = 1; i < pending->size(); ++i)
    (*pending)[i].Clear();
}

void tesseract::Wordrec::SaveAltChoices	(	const LIST &	best_choices,
		WERD_RES *	word
	)

void tesseract::Wordrec::SegSearch	(	WERD_RES *	word_res,
		BestChoiceBundle *	best_choice_bundle,
		BlamerBundle *	blamer_bundle
	)

Definition at line 37 of file segsearch.cpp.

                                                     {
  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());
  }
}

bool tesseract::Wordrec::SegSearchDone ( int num_futile_classifications ) [inline, protected]

Definition at line 426 of file wordrec.h.

                                                            {
    return (language_model_->AcceptableChoiceFound() ||
            num_futile_classifications >=
            segsearch_max_futile_classifications);
  }

int tesseract::Wordrec::select_blob_to_split	(	const GenericVector< BLOB_CHOICE * > &	blob_choices,
		float	rating_ceiling,
		bool	split_next_to_fragment
	)

Definition at line 541 of file chopper.cpp.

                                                       {
  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;
}

int tesseract::Wordrec::select_blob_to_split_from_fixpt ( DANGERR * fixpt )

Definition at line 633 of file chopper.cpp.

                                                           {
  if (!fixpt)
    return -1;
  for (int i = 0; i < fixpt->size(); i++) {
    if ((*fixpt)[i].begin + 1 == (*fixpt)[i].end &&
        (*fixpt)[i].dangerous &&
        (*fixpt)[i].correct_is_ngram) {
      return (*fixpt)[i].begin;
    }
  }
  return -1;
}

void tesseract::Wordrec::set_pass1 ( )

Definition at line 85 of file tface.cpp.

                        {
  chop_ok_split.set_value(70.0);
  language_model_->getParamsModel().SetPass(ParamsModel::PTRAIN_PASS1);
  SettupPass1();
}

void tesseract::Wordrec::set_pass2 ( )

Definition at line 97 of file tface.cpp.

                        {
  chop_ok_split.set_value(pass2_ok_split);
  language_model_->getParamsModel().SetPass(ParamsModel::PTRAIN_PASS2);
  SettupPass2();
}

void tesseract::Wordrec::try_point_pairs	(	EDGEPT *	points[MAX_NUM_POINTS],
		inT16	num_points,
		SeamQueue *	seam_queue,
		SeamPile *	seam_pile,
		SEAM **	seam,
		TBLOB *	blob
	)

Definition at line 297 of file findseam.cpp.

                                            {
  inT16 x;
  inT16 y;
  PRIORITY priority;

  for (x = 0; x < num_points; x++) {
    for (y = x + 1; y < num_points; y++) {
      if (points[y] &&
          points[x]->WeightedDistance(*points[y], chop_x_y_weight) <
              chop_split_length &&
          points[x] != points[y]->next && points[y] != points[x]->next &&
          !is_exterior_point(points[x], points[y]) &&
          !is_exterior_point(points[y], points[x])) {
        SPLIT split(points[x], points[y]);
        priority = partial_split_priority(&split);

        choose_best_seam(seam_queue, &split, priority, seam, blob, seam_pile);
      }
    }
  }
}

void tesseract::Wordrec::try_vertical_splits	(	EDGEPT *	points[MAX_NUM_POINTS],
		inT16	num_points,
		EDGEPT_CLIST *	new_points,
		SeamQueue *	seam_queue,
		SeamPile *	seam_pile,
		SEAM **	seam,
		TBLOB *	blob
	)

Definition at line 335 of file findseam.cpp.

                                                {
  EDGEPT *vertical_point = NULL;
  inT16 x;
  PRIORITY priority;
  TESSLINE *outline;

  for (x = 0; x < num_points; x++) {
    vertical_point = NULL;
    for (outline = blob->outlines; outline; outline = outline->next) {
      vertical_projection_point(points[x], outline->loop,
                                &vertical_point, new_points);
    }

    if (vertical_point && points[x] != vertical_point->next &&
        vertical_point != points[x]->next &&
        points[x]->WeightedDistance(*vertical_point, chop_x_y_weight) <
            chop_split_length) {
      SPLIT split(points[x], vertical_point);
      priority = partial_split_priority(&split);
      choose_best_seam(seam_queue, &split, priority, seam, blob, seam_pile);
    }
  }
}

void tesseract::Wordrec::UpdateSegSearchNodes	(	float	rating_cert_scale,
		int	starting_col,
		GenericVector< SegSearchPending > *	pending,
		WERD_RES *	word_res,
		LMPainPoints *	pain_points,
		BestChoiceBundle *	best_choice_bundle,
		BlamerBundle *	blamer_bundle
	)		`[protected]`

Definition at line 194 of file segsearch.cpp.

                                 {
  MATRIX *ratings = word_res->ratings;
  ASSERT_HOST(ratings->dimension() == pending->size());
  ASSERT_HOST(ratings->dimension() == best_choice_bundle->beam.size());
  for (int col = starting_col; col < ratings->dimension(); ++col) {
    if (!(*pending)[col].WorkToDo()) continue;
    int first_row = col;
    int last_row = MIN(ratings->dimension() - 1,
                       col + ratings->bandwidth() - 1);
    if ((*pending)[col].SingleRow() >= 0) {
      first_row = last_row = (*pending)[col].SingleRow();
    }
    if (segsearch_debug_level > 0) {
      tprintf("\n\nUpdateSegSearchNodes: col=%d, rows=[%d,%d], alljust=%d\n",
              col, first_row, last_row,
              (*pending)[col].IsRowJustClassified(MAX_INT32));
    }
    // Iterate over the pending list for this column.
    for (int row = first_row; row <= last_row; ++row) {
      // Update language model state of this child+parent pair.
      BLOB_CHOICE_LIST *current_node = ratings->get(col, row);
      LanguageModelState *parent_node =
          col == 0 ? NULL : best_choice_bundle->beam[col - 1];
      if (current_node != NULL &&
          language_model_->UpdateState((*pending)[col].IsRowJustClassified(row),
                                       col, row, current_node, parent_node,
                                       pain_points, word_res,
                                       best_choice_bundle, blamer_bundle) &&
          row + 1 < ratings->dimension()) {
        // Since the language model state of this entry changed, process all
        // the child column.
        (*pending)[row + 1].RevisitWholeColumn();
        if (segsearch_debug_level > 0) {
          tprintf("Added child col=%d to pending\n", row + 1);
        }
      }  // end if UpdateState.
    }  // end for row.
  }  // end for col.
  if (best_choice_bundle->best_vse != NULL) {
    ASSERT_HOST(word_res->StatesAllValid());
    if (best_choice_bundle->best_vse->updated) {
      pain_points->GenerateFromPath(rating_cert_scale,
                                    best_choice_bundle->best_vse, word_res);
      if (!best_choice_bundle->fixpt.empty()) {
        pain_points->GenerateFromAmbigs(best_choice_bundle->fixpt,
                                        best_choice_bundle->best_vse, word_res);
      }
    }
  }
  // The segsearch is completed. Reset all updated flags on all VSEs and reset
  // all pendings.
  for (int col = 0; col < pending->size(); ++col) {
    (*pending)[col].Clear();
    ViterbiStateEntry_IT
        vse_it(&best_choice_bundle->beam[col]->viterbi_state_entries);
    for (vse_it.mark_cycle_pt(); !vse_it.cycled_list(); vse_it.forward()) {
      vse_it.data()->updated = false;
    }
  }
}

void tesseract::Wordrec::vertical_projection_point	(	EDGEPT *	split_point,
		EDGEPT *	target_point,
		EDGEPT **	best_point,
		EDGEPT_CLIST *	new_points
	)

Definition at line 278 of file chop.cpp.

     {
    if (((p->pos.x <= x && x <= p->next->pos.x) ||
         (p->next->pos.x <= x && x <= p->pos.x)) &&
        !same_point(split_point->pos, p->pos) &&
        !same_point(split_point->pos, p->next->pos) &&
        !p->IsChopPt() &&
        (*best_point == NULL || !same_point((*best_point)->pos, p->pos))) {

      if (near_point(split_point, p, p->next, &this_edgept)) {
        new_point_it.add_before_then_move(this_edgept);
      }

      if (*best_point == NULL)
        best_dist = edgept_dist (split_point, this_edgept);

      this_edgept =
        pick_close_point(split_point, this_edgept, &best_dist);
      if (this_edgept)
        *best_point = this_edgept;
    }

    p = p->next;
  }
  while (p != target_point);
}

}  // namespace tesseract

void tesseract::Wordrec::WordSearch ( WERD_RES * word_res )

Definition at line 130 of file segsearch.cpp.

                                           {
  LMPainPoints pain_points(segsearch_max_pain_points,
                           segsearch_max_char_wh_ratio,
                           assume_fixed_pitch_char_segment,
                           &getDict(), segsearch_debug_level);
  GenericVector<SegSearchPending> pending;
  BestChoiceBundle best_choice_bundle(word_res->ratings->dimension());
  // Run Segmentation Search.
  InitialSegSearch(word_res, &pain_points, &pending, &best_choice_bundle, NULL);
  if (segsearch_debug_level > 0) {
    tprintf("Ending ratings matrix%s:\n",
            wordrec_enable_assoc ? " (with assoc)" : "");
    word_res->ratings->print(getDict().getUnicharset());
  }
}