INT16 resegment_box( //
ROW *row,
BOX box,
char *ch,
INT16 block_id,
INT16 row_id,
INT16 boxfile_lineno,
INT16 boxfile_charno) {
WERD_IT word_it;
WERD *word;
WERD *new_word = NULL;
BOOL8 polyg = false;
PBLOB_IT blob_it;
PBLOB_IT new_blob_it;
PBLOB *blob;
PBLOB *new_blob;
OUTLINE_IT outline_it;
OUTLINE_LIST dummy; // Just to initialize new_outline_it.
OUTLINE_IT new_outline_it = &dummy;
OUTLINE *outline;
BOX new_word_box;
float word_x_centre;
float baseline;
INT16 error_count = 0; //number of chars lost
word_it.set_to_list (row->word_list ());
for (word_it.mark_cycle_pt (); !word_it.cycled_list (); word_it.forward ()) {
word = word_it.data ();
polyg = word->flag (W_POLYGON);
if (word->bounding_box ().overlap (box)) {
blob_it.set_to_list (word->gblob_list ());
for (blob_it.mark_cycle_pt ();
!blob_it.cycled_list (); blob_it.forward ()) {
blob = blob_it.data ();
if (gblob_bounding_box (blob, polyg).overlap (box)) {
outline_it.set_to_list (gblob_out_list (blob, polyg));
for (outline_it.mark_cycle_pt ();
!outline_it.cycled_list (); outline_it.forward ()) {
outline = outline_it.data ();
if (goutline_bounding_box (outline, polyg).
major_overlap (box)) {
if (strlen (word->text ()) > 0) {
if (error_count == 0) {
error_count = 1;
if (applybox_debug > 4)
report_failed_box (boxfile_lineno,
boxfile_charno,
box, ch,
"FAILURE! box overlaps blob in labelled word");
}
if (applybox_debug > 4)
tprintf
("APPLY_BOXES: ALSO ignoring corrupted char blk:%d row:%d \"%s\"\n",
block_id, row_id,
word_it.data ()->text ());
word_it.data ()->set_text ("");
//UN label it
error_count++;
}
if (error_count == 0) {
if (new_word == NULL) {
/* Make a new word with a single blob */
new_word = word->shallow_copy ();
new_word->set_text (ch);
if (polyg)
new_blob = new PBLOB;
else
new_blob = (PBLOB *) new C_BLOB;
new_blob_it.set_to_list (new_word->
gblob_list ());
new_blob_it.add_to_end (new_blob);
new_outline_it.
set_to_list (gblob_out_list
(new_blob, polyg));
}
new_outline_it.add_to_end (outline_it.
extract ());
//move blob
}
}
}
//no outlines in blob
if (outline_it.empty ())
//so delete blob
delete blob_it.extract ();
}
}
if (blob_it.empty ()) //no blobs in word
//so delete word
delete word_it.extract ();
}
}
if (error_count > 0)
return error_count;
if (new_word != NULL) {
gblob_sort_list (new_word->gblob_list (), polyg);
word_it.add_to_end (new_word);
new_word_box = new_word->bounding_box ();
word_x_centre = (new_word_box.left () + new_word_box.right ()) / 2.0f;
baseline = row->base_line (word_x_centre);
if (STRING (chs_caps_ht).contains (ch[0]) &&
(new_word_box.top () <
baseline + (1 + applybox_error_band) * row->x_height ())) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! caps-ht char didn't ascend");
new_word->set_text ("");
return 1;
}
if (STRING (chs_odd_top).contains (ch[0]) &&
(new_word_box.top () <
baseline + (1 - applybox_error_band) * row->x_height ())) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! Odd top char below xht");
new_word->set_text ("");
return 1;
}
if (STRING (chs_x_ht).contains (ch[0]) &&
((new_word_box.top () >
baseline + (1 + applybox_error_band) * row->x_height ()) ||
(new_word_box.top () <
baseline + (1 - applybox_error_band) * row->x_height ()))) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! x-ht char didn't have top near xht");
new_word->set_text ("");
return 1;
}
if (STRING (chs_non_ambig_bl).contains (ch[0]) &&
((new_word_box.bottom () <
baseline - applybox_error_band * row->x_height ()) ||
(new_word_box.bottom () >
baseline + applybox_error_band * row->x_height ()))) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! non ambig BL char didnt have bottom near baseline");
new_word->set_text ("");
return 1;
}
if (STRING (chs_odd_bot).contains (ch[0]) &&
(new_word_box.bottom () >
baseline + applybox_error_band * row->x_height ())) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! Odd bottom char above baseline");
new_word->set_text ("");
return 1;
}
if (STRING (chs_desc).contains (ch[0]) &&
(new_word_box.bottom () >
baseline - applybox_error_band * row->x_height ())) {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! Descender doesn't descend");
new_word->set_text ("");
return 1;
}
return 0;
}
else {
report_failed_box (boxfile_lineno, boxfile_charno, box, ch,
"FAILURE! Couldn't find any blobs");
return 1;
}
}
/// Consume all source blobs that strongly overlap the given box,
/// putting them into a new word, with the correct_text label.
/// Fights over which box owns which blobs are settled by
/// applying the blobs to box or next_box with the least non-overlap.
/// @return false if the box was in error, which can only be caused by
/// failing to find an overlapping blob for a box.
bool Tesseract::ResegmentWordBox(BLOCK_LIST *block_list,
const TBOX& box, const TBOX& next_box,
const char* correct_text) {
if (applybox_debug > 1) {
tprintf("\nAPPLY_BOX: in ResegmentWordBox() for %s\n", correct_text);
}
WERD* new_word = NULL;
BLOCK_IT b_it(block_list);
for (b_it.mark_cycle_pt(); !b_it.cycled_list(); b_it.forward()) {
BLOCK* block = b_it.data();
if (!box.major_overlap(block->bounding_box()))
continue;
ROW_IT r_it(block->row_list());
for (r_it.mark_cycle_pt(); !r_it.cycled_list(); r_it.forward()) {
ROW* row = r_it.data();
if (!box.major_overlap(row->bounding_box()))
continue;
WERD_IT w_it(row->word_list());
for (w_it.mark_cycle_pt(); !w_it.cycled_list(); w_it.forward()) {
WERD* word = w_it.data();
if (applybox_debug > 2) {
tprintf("Checking word:");
word->bounding_box().print();
}
if (word->text() != NULL && word->text()[0] != '\0')
continue; // Ignore words that are already done.
if (!box.major_overlap(word->bounding_box()))
continue;
C_BLOB_IT blob_it(word->cblob_list());
for (blob_it.mark_cycle_pt(); !blob_it.cycled_list();
blob_it.forward()) {
C_BLOB* blob = blob_it.data();
TBOX blob_box = blob->bounding_box();
if (!blob_box.major_overlap(box))
continue;
double current_box_miss_metric = BoxMissMetric(blob_box, box);
double next_box_miss_metric = BoxMissMetric(blob_box, next_box);
if (applybox_debug > 2) {
tprintf("Checking blob:");
blob_box.print();
tprintf("Current miss metric = %g, next = %g\n",
current_box_miss_metric, next_box_miss_metric);
}
if (current_box_miss_metric > next_box_miss_metric)
continue; // Blob is a better match for next box.
if (applybox_debug > 2) {
tprintf("Blob match: blob:");
blob_box.print();
tprintf("Matches box:");
box.print();
tprintf("With next box:");
next_box.print();
}
if (new_word == NULL) {
// Make a new word with a single blob.
new_word = word->shallow_copy();
new_word->set_text(correct_text);
w_it.add_to_end(new_word);
}
C_BLOB_IT new_blob_it(new_word->cblob_list());
new_blob_it.add_to_end(blob_it.extract());
}
}
}
}
if (new_word == NULL && applybox_debug > 0) tprintf("FAIL!\n");
return new_word != NULL;
}