mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-11-24 02:59:07 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Don't drop words with low certainty (#1264)

Browse Source 
Fix #681.
This commit is contained in:
Amit D 2018-02-20 18:19:10 +02:00 committed by zdenop
parent af6994efd9
commit 766b7bd620
1 changed files with 2 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
ccmain/linerec.cpp
View File

@ -291,21 +291,8 @@ void Tesseract::SearchWords(PointerVector<WERD_RES>* words) {
word->best_choice->print();
}
word->best_choice->set_certainty(word_certainty);
// 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->tess_accepted = stopper_dict->AcceptableResult(word);
}
}
}