4

I was going through the c++ API part of tesseract and found this snippet of code for getting each symbol from a text.

  Pix *image = pixRead("/usr/src/tesseract-3.02/phototest.tif");
  tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
  api->Init(NULL, "eng");
  api->SetImage(image);
  api->SetVariable("save_blob_choices", "T");
  api->SetRectangle(37, 228, 548, 31);
  api->Recognize(NULL);

  tesseract::ResultIterator* ri = api->GetIterator();
  tesseract::PageIteratorLevel level = tesseract::RIL_SYMBOL;
  if(ri != 0) {
      do {
          const char* symbol = ri->GetUTF8Text(level);
          float conf = ri->Confidence(level);
          if(symbol != 0) {
              printf("symbol %s, conf: %f", symbol, conf);
              bool indent = false;
              tesseract::ChoiceIterator ci(*ri);
              do {
                  if (indent) printf("\t\t ");
                  printf("\t- ");
                  const char* choice = ci.GetUTF8Text();
                  printf("%s conf: %f\n", choice, ci.Confidence());
                  indent = true;
              } while(ci.Next());
          }
          printf("---------------------------------------------\n");
          delete[] symbol;
      } while((ri->Next(level)));
  }

Now if we give the wrong dimensions for this bounding box(api->setRectangle) it doesn't give you the required text. So is there a way to estimate these dimensions in tesseract. Link to the source https://code.google.com/p/tesseract-ocr/wiki/APIExample#Example_of_iterator_over_the_classifier_choices_for_a_single_sym

4

0 回答 0