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
}
int main(int argc, char *argv[])
{
if(argc < 2)
{
cout << "Usage: main <image-file-name>" << endl;
exit(0);
}
// load the image
Mat img = imread(argv[1]);
//references = getReferences();//load the reference images
tess.Init(NULL, NULL, tesseract::OEM_DEFAULT);
tess.SetVariable("tessedit_char_whitelist", "0123456789");
//for speed testing
/*double t0 = (double) getTickCount();/
for(int i = 0; i < 100; i++)
{
signDetection(img);
}
double t1 = (double) getTickCount();
cout << (t1-t0) / getTickFrequency() << endl;*/
signDetection(img);
waitKey(0);
return 0;
}
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;
}
int tess_capi_get_ocr(PIX *pix,char *outstr,int maxlen,FILE *out)
{
STRING text_out;
if (!api.ProcessPage(pix,0,NULL,NULL,0,&text_out))
{
/* pixDestroy(&pix); */
if (out!=NULL)
fprintf(out,"tesscapi: Error during bitmap processing.\n");
api.Clear();
return(-1);
}
strncpy(outstr,text_out.string(),maxlen-1);
outstr[maxlen-1]='\0';
api.Clear();
return(0);
}
int SubsExtractor::ocr(char *outtext)
{
Mat crop,crop2;
Mat(img, ROI).copyTo(crop);
cvtColor(crop, crop2, CV_BGR2GRAY);
//adaptiveThreshold(crop2,crop,255,CV_ADAPTIVE_THRESH_GAUSSIAN_C,CV_THRESH_BINARY,3,5);
int th1 = 200;
int th2 = 255;
threshold(crop2,crop,th1,th2,THRESH_BINARY);
//tesseract::TessBaseAPI tess;
tess.SetImage((uchar *)crop.data,crop.cols,crop.rows,1,crop.cols);
imshow("control", crop);
char *s;
if((s = tess.GetUTF8Text()) != NULL) {
//fprintf(stderr,"OCR: %s\n",s);
strcpy(outtext,s);
return strlen(outtext);
}
return 0;
}
int detectNumber(Mat img){
//Mat circ = copyContour(img, circle);
inRange(img, Scalar(0, 0, 51), Scalar(255, 255, 255), img); //filter black
tess.SetImage((uchar*)img.data, img.size().width, img.size().height, img.channels(), img.step1());
//tess.SetRectangle(circle[0]-circle[2], circle[1]-circle[2],2*circle[2],2*circle[2]);
string out = string (tess.GetUTF8Text());
out.erase( std::remove_if( out.begin(), out.end(), ::isspace ), out.end() );
const char* result = out.c_str();
//printf("%s\n", result);
switch(atoi(result)){
case 10: return 5;
case 20: return 6;
case 30: return 7;
case 40: return 8;
case 50: return 9;
case 60: return 10;
case 70: return 11;
case 80: return 12;
}
//rectangle(img, Point(circle[0]-circle[2], circle[1]-circle[2]), Point(circle[0]+circle[2], circle[1]+circle[2]), Scalar (100,255,255),3,8,0);
// imwrite("./test.png", img);
return -1;}
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());
// }
}
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, "");
}
void TesseractBridge::close() {
api.End();
}
void run(Mat& image, string& output, vector<Rect>* component_rects=NULL,
vector<string>* component_texts=NULL, vector<float>* component_confidences=NULL,
int component_level=0)
{
CV_Assert( (image.type() == CV_8UC1) || (image.type() == CV_8UC3) );
#ifdef HAVE_TESSERACT
if (component_texts != 0)
component_texts->clear();
if (component_rects != 0)
component_rects->clear();
if (component_confidences != 0)
component_confidences->clear();
tess.SetImage((uchar*)image.data, image.size().width, image.size().height, image.channels(), image.step1());
tess.Recognize(0);
char *outText;
outText = tess.GetUTF8Text();
output = string(outText);
delete [] outText;
if ( (component_rects != NULL) || (component_texts != NULL) || (component_confidences != NULL) )
{
tesseract::ResultIterator* ri = tess.GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_WORD;
if (component_level == OCR_LEVEL_TEXTLINE)
level = tesseract::RIL_TEXTLINE;
if (ri != 0) {
do {
const char* word = ri->GetUTF8Text(level);
if (word == NULL)
continue;
float conf = ri->Confidence(level);
int x1, y1, x2, y2;
ri->BoundingBox(level, &x1, &y1, &x2, &y2);
if (component_texts != 0)
component_texts->push_back(string(word));
if (component_rects != 0)
component_rects->push_back(Rect(x1,y1,x2-x1,y2-y1));
if (component_confidences != 0)
component_confidences->push_back(conf);
delete[] word;
} while (ri->Next(level));
}
delete ri;
}
tess.Clear();
#else
cout << "OCRTesseract(" << component_level << image.type() <<"): Tesseract not found." << endl;
output.clear();
if(component_rects)
component_rects->clear();
if(component_texts)
component_texts->clear();
if(component_confidences)
component_confidences->clear();
#endif
}
~OCRTesseractImpl()
{
#ifdef HAVE_TESSERACT
tess.End();
#endif
}
/*
** 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);
}
void tess_capi_end(void)
{
api.End();
}
