// Returns true if *this and other agree on the baseline and x-height
// to within some tolerance based on a given estimate of the x-height.
bool BLOB_CHOICE::PosAndSizeAgree(const BLOB_CHOICE& other, float x_height,
bool debug) const {
double baseline_diff = fabs(yshift() - other.yshift());
if (baseline_diff > kMaxBaselineDrift * x_height) {
if (debug) {
tprintf("Baseline diff %g for %d v %d\n",
baseline_diff, unichar_id_, other.unichar_id_);
}
return false;
}
double this_range = max_xheight() - min_xheight();
double other_range = other.max_xheight() - other.min_xheight();
double denominator = ClipToRange(MIN(this_range, other_range),
1.0, kMaxOverlapDenominator * x_height);
double overlap = MIN(max_xheight(), other.max_xheight()) -
MAX(min_xheight(), other.min_xheight());
overlap /= denominator;
if (debug) {
tprintf("PosAndSize for %d v %d: bl diff = %g, ranges %g, %g / %g ->%g\n",
unichar_id_, other.unichar_id_, baseline_diff,
this_range, other_range, denominator, overlap);
}
return overlap >= kMinXHeightMatch;
}
// Creates a fake blob choice from the combination of the given fragments.
// unichar is the class to be made from the combination,
// expanded_fragment_lengths[choice_index] is the number of fragments to use.
// old_choices[choice_index] has the classifier output for each fragment.
// choice index initially indexes the last fragment and should be decremented
// expanded_fragment_lengths[choice_index] times to get the earlier fragments.
// Guarantees to return something non-null, or abort!
BLOB_CHOICE* Wordrec::rebuild_fragments(
const char* unichar,
const char* expanded_fragment_lengths,
int choice_index,
BLOB_CHOICE_LIST_VECTOR *old_choices) {
float rating = 0.0f;
float certainty = 0.0f;
inT16 min_xheight = -MAX_INT16;
inT16 max_xheight = MAX_INT16;
for (int fragment_pieces = expanded_fragment_lengths[choice_index] - 1;
fragment_pieces >= 0; --fragment_pieces, --choice_index) {
// Get a pointer to the classifier results from the old_choices.
BLOB_CHOICE_LIST *current_choices = old_choices->get(choice_index);
// 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.
CHAR_FRAGMENT fragment;
fragment.set_all(unichar, fragment_pieces,
expanded_fragment_lengths[choice_index], false);
BLOB_CHOICE_IT choice_it(current_choices);
for (choice_it.mark_cycle_pt(); !choice_it.cycled_list();
choice_it.forward()) {
BLOB_CHOICE* choice = choice_it.data();
const CHAR_FRAGMENT *current_fragment =
getDict().getUnicharset().get_fragment(choice->unichar_id());
if (current_fragment && fragment.equals(current_fragment)) {
rating += choice->rating();
if (choice->certainty() < certainty) {
certainty = choice->certainty();
}
IntersectRange(choice->min_xheight(), choice->max_xheight(),
&min_xheight, &max_xheight);
break;
}
}
if (choice_it.cycled_list()) {
print_ratings_list("Failure", current_choices, unicharset);
tprintf("Failed to find fragment %s at index=%d\n",
fragment.to_string().string(), choice_index);
}
ASSERT_HOST(!choice_it.cycled_list()); // Be sure we found the fragment.
}
return new BLOB_CHOICE(getDict().getUnicharset().unichar_to_id(unichar),
rating, certainty, -1, -1, 0,
min_xheight, max_xheight, false);
}