Hi
if someone can help me with a tessaract (API-4.01) C ++ example, how can I
create a searchable pdf
example below does not work
i get a pdf output file but pdf output file is not readable
Kinds Regards
Ivica Anic
###########################################################################
const char* output_baseqq = "my_first_tesseract_pdfqq";
char *datapath = "C:\\Users\\iOCRKonverter3\\redist";
int timeout_msq = 5000;
const char* retry_configq = nullptr;
bool textonlyq = false;
int jpg_qualityq = 92;
//Pix *p = pixRead(inputImage.c_str());
PIXA *sourceImg__ = pixaReadMultipageTiff(inputImage.c_str());
tesseract::TessBaseAPI *apiq = new tesseract::TessBaseAPI();
apiq->SetPageSegMode(tesseract::PSM_AUTO_ONLY);
if (apiq->Init(datapath, "deu", tesseract::OEM_DEFAULT)) {
fprintf(stderr, "Could not initialize tesseract.\n");
exit(1);
}
if (sourceImg__->n > 0) {
for (int i = 0; i < sourceImg__->n; i++) {
Pix* image = sourceImg__->pix[i];
pixScale(image, 4.167, 4.167);
apiq->SetImage(image);
}
}
apiq->Recognize(0);
apiq->SetInputName(inputImage.c_str());
apiq->SetOutputName(output_baseqq);
//tesseract::TessResultRenderer *rendererq1 = new
tesseract::TessPDFRenderer(apiq->GetDatapath());
tesseract::TessPDFRenderer *rendererq = new
tesseract::TessPDFRenderer(output_baseqq, apiq->GetDatapath(), textonlyq);
rendererq->BeginDocument("test");
rendererq->AddImage(apiq);
//bool succeed = false;
bool succeed = apiq->ProcessPages(inputImage.c_str(), retry_configq,
timeout_msq, rendererq);
rendererq->EndDocument();
if (!succeed) {
fprintf(stderr, "Error during processing.\n");
return EXIT_FAILURE;
}
apiq->End();
return EXIT_SUCCESS;
--
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/6b8af466-d084-4640-8b19-4f21fe1559d7%40googlegroups.com.
