void testtess() {
cv::Mat img = imread("phototest.png");
if(img.empty()) { cerr << "noup." << endl; return; }
imshow("blah",img);
waitKey(1);
cout << "photo " << img.size() << endl;
int rc = api.Init(tessdata_dir.c_str(), "ara", tesseract::OEM_DEFAULT);
if (rc) {
cerr << "Could not initialize tesseract.\n";
exit(1);
}
api.SetPageSegMode(tesseract::PSM_AUTO);
printf("Tesseract Open Source OCR Engine v%s with Leptonica\n",
tesseract::TessBaseAPI::Version());
printf("Init languages %s\n",api.GetInitLanguagesAsString());
Mat tmp; cvtColor(img, tmp, CV_BGR2GRAY);
adaptiveThreshold(tmp, tmp, 255, ADAPTIVE_THRESH_MEAN_C, THRESH_BINARY, 51, 35);
imshow("eqhist", tmp);
// cvtColor(tmp, out(Rect(0,0,r.width,r.height)), CV_GRAY2BGR);
char* cstr = api.TesseractRect(tmp.data, tmp.channels(), tmp.cols*tmp.channels(), 0, 0, tmp.cols, tmp.rows);
cout << cstr << endl;
delete[] cstr;
waitKey(0);
}
pair<int,string> TesseractBridge::processEx(const Mat& tmp, Rect& r) {
api.Clear();
char* cstr = api.TesseractRect(tmp.data, tmp.channels(), tmp.cols*tmp.channels(), 0, 0, tmp.cols, tmp.rows);
// cout << cstr << endl;
delete[] cstr;
tesseract::ResultIterator* ri = api.GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
if (ri != 0) {
const char* word = ri->GetUTF8Text(level);
if(!word) return make_pair(0, "");
float conf = ri->Confidence(level);
int x1, y1, x2, y2;
ri->BoundingBox(level, &x1, &y1, &x2, &y2);
// printf("word: '%s'; \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n",
// word, conf, x1, y1, x2, y2);
string theword(word);
delete[] word;
bool allnonalphanom = true;
for (int i=0; i<theword.size(); i++) {
allnonalphanom = allnonalphanom && !(isalnum(theword[i]) || theword[i] == '"' || theword[i] == '.' || theword[i] == ',' || theword[i] == '?' || theword[i] == '!' || theword[i] == '\'');
}
if (allnonalphanom) return make_pair(0, "");
r.x += x1;
r.y += y1;
r.width = x2-x1;
r.height = y2-y1;
return make_pair((int)conf, theword);
} else
return make_pair(0, "");
}
