double ComputeWordError(string* truth_str, string* ocr_str) {
using StrMap = std::unordered_map<std::string, int,
std::hash<std::string>>;
//GenericVector<string> truth_words, ocr_words;
truth_str->split(' ', &truth_words);
if (truth_words.empty()) return 0.0;
ocr_str->split(' ', &ocr_words);
StrMap word_counts;
for (int i = 0; i < truth_words.size(); ++i) {
std::string truth_word(truth_words[i].string());
auto it = word_counts.find(truth_word);
if (it == word_counts.end())
word_counts.insert(std::make_pair(truth_word, 1));
else
++it->second;
}
for (int i = 0; i < ocr_words.size(); ++i) {
std::string ocr_word(ocr_words[i].string());
auto it = word_counts.find(ocr_word);
if (it == word_counts.end())
word_counts.insert(std::make_pair(ocr_word, -1));
else
--it->second;
}
int word_recall_errs = 0;
for (StrMap::const_iterator it = word_counts.begin(); it !=
word_counts.end();
++it) {
if (it->second > 0) word_recall_errs += it->second;
}
return static_cast<double>(word_recall_errs) / truth_words.size();
}
I want to understand the above code as I dont have much knowledge of c++
language.
Thank You
Meet Yogi
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/3ae7a2f1-224e-4c72-91e3-37616a7bf970n%40googlegroups.com.
