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);
}
//Default constructor
OCRTesseractImpl(const char* datapath, const char* language, const char* char_whitelist, int oemode, int psmode)
{
#ifdef HAVE_TESSERACT
const char *lang = "eng";
if (language != NULL)
lang = language;
if (tess.Init(datapath, lang, (tesseract::OcrEngineMode)oemode))
{
cout << "OCRTesseract: Could not initialize tesseract." << endl;
throw 1;
}
//cout << "OCRTesseract: tesseract version " << tess.Version() << endl;
tesseract::PageSegMode pagesegmode = (tesseract::PageSegMode)psmode;
tess.SetPageSegMode(pagesegmode);
if(char_whitelist != NULL)
tess.SetVariable("tessedit_char_whitelist", char_whitelist);
else
tess.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ");
tess.SetVariable("save_best_choices", "T");
#else
cout << "OCRTesseract("<<oemode<<psmode<<"): Tesseract not found." << endl;
if (datapath != NULL)
cout << " " << datapath << endl;
if (language != NULL)
cout << " " << language << endl;
if (char_whitelist != NULL)
cout << " " << char_whitelist << endl;
#endif
}
std::string identifyText(cv::Mat input, std::string language)
{
ocr.Init(NULL, language.c_str(), tesseract::OEM_TESSERACT_ONLY);
//std::string whitelist = "АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюяabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789,.:";
//ocr.SetVariable("tessedit_char_whitelist", whitelist.c_str());
ocr.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);
ocr.SetImage(input.data, input.cols, input.rows, 1, input.step);
std::string text = ocr.GetUTF8Text();
return text;
}
void TesseractBridge::init() {
// int rc = api.Init(tessdata_dir.c_str(), NULL);
// if (rc) {
// cerr << "Could not initialize tesseract.\n";
// exit(1);
// }
// api.End();
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());
// GenericVector<STRING> v; api.GetAvailableLanguagesAsVector(&v);
// for (int i = 0; i < v.length(); ++i) {
// printf("lang %s\n",v[i].string());
// }
}
/*
** ocr_type=0: OEM_DEFAULT
** ocr_type=1: OEM_TESSERACT_ONLY
** ocr_type=2: OEM_CUBE_ONLY
** ocr_type=3: OEM_TESSERACT_CUBE_COMBINED
*/
int tess_capi_init(char *datapath,char *language,int ocr_type,FILE *out,
char *initstr,int maxlen)
{
int status;
#ifdef USE_NLS
setlocale (LC_ALL, "");
bindtextdomain (PACKAGE, LOCALEDIR);
textdomain (PACKAGE);
#endif
// fprintf(stderr, "tesseract %s\n", tesseract::TessBaseAPI::Version());
// Make the order of args a bit more forgiving than it used to be.
const char* lang = "eng";
tesseract::PageSegMode pagesegmode = tesseract::PSM_SINGLE_BLOCK;
if (language!=NULL && language[0]!='\0')
lang = language;
/*
if (output == NULL)
{
fprintf(stderr, _("Usage:%s imagename outputbase [-l lang] "
"[-psm pagesegmode] [configfile...]\n"), argv[0]);
fprintf(stderr,
_("pagesegmode values are:\n"
"0 = Orientation and script detection (OSD) only.\n"
"1 = Automatic page segmentation with OSD.\n"
"2 = Automatic page segmentation, but no OSD, or OCR\n"
"3 = Fully automatic page segmentation, but no OSD. (Default)\n"
"4 = Assume a single column of text of variable sizes.\n"
"5 = Assume a single uniform block of vertically aligned text.\n"
"6 = Assume a single uniform block of text.\n"
"7 = Treat the image as a single text line.\n"
"8 = Treat the image as a single word.\n"
"9 = Treat the image as a single word in a circle.\n"
"10 = Treat the image as a single character.\n"));
fprintf(stderr, _("-l lang and/or -psm pagesegmode must occur before any"
"configfile.\n"));
exit(1);
}
*/
api.SetOutputName(NULL);
status=api.Init(datapath,lang,
ocr_type==0 ? tesseract::OEM_DEFAULT :
(ocr_type==1 ? tesseract::OEM_TESSERACT_ONLY :
(ocr_type==2 ? tesseract::OEM_CUBE_ONLY :
(tesseract::OEM_TESSERACT_CUBE_COMBINED))));
if (status)
return(status);
/*
api.Init("tesscapi",lang,tesseract::OEM_DEFAULT,
&(argv[arg]), argc - arg, NULL, NULL, false);
*/
// We have 2 possible sources of pagesegmode: a config file and
// the command line. For backwards compatability reasons, the
// default in tesseract is tesseract::PSM_SINGLE_BLOCK, but the
// default for this program is tesseract::PSM_AUTO. We will let
// the config file take priority, so the command-line default
// can take priority over the tesseract default, so we use the
// value from the command line only if the retrieved mode
// is still tesseract::PSM_SINGLE_BLOCK, indicating no change
// in any config file. Therefore the only way to force
// tesseract::PSM_SINGLE_BLOCK is from the command line.
// It would be simpler if we could set the value before Init,
// but that doesn't work.
if (api.GetPageSegMode() == tesseract::PSM_SINGLE_BLOCK)
api.SetPageSegMode(pagesegmode);
/*
** Initialization message
*/
{
char istr[256];
sprintf(istr,"Tesseract Open Source OCR Engine v%s ",tesseract::TessBaseAPI::Version());
if (ocr_type==0 || ocr_type==3)
sprintf(&istr[strlen(istr)],"[CUBE+] (lang=");
else if (ocr_type==2)
sprintf(&istr[strlen(istr)],"[CUBE] (lang=");
strncpy(&istr[strlen(istr)],language,253-strlen(istr));
istr[253]='\0';
strcat(istr,")");
if (out!=NULL)
fprintf(out,"%s\n",istr);
if (initstr!=NULL)
{
strncpy(initstr,istr,maxlen-1);
initstr[maxlen-1]='\0';
}
}
/* Turn off CUBE debugging output */
api.SetVariable("cube_debug_level","0");
#if (WILLUSDEBUG & 1)
api.SetVariable("cube_debug_level","9");
api.SetVariable("paragraph_debug_level","9");
api.SetVariable("tessdata_manager_debug_level","9");
api.SetVariable("tosp_debug_level","9");
api.SetVariable("wordrec_debug_level","9");
api.SetVariable("segsearch_debug_level","9");
#endif
return(0);
}