Hello,
I want to get each words in a text line by word iterator.But it isnot clear
for me.
My code is below. Do you have any idea?
Pix *image = pixRead("ex.jpg");
tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
api->Init(NULL, "eng");
api->SetImage(image);
api->Recognize(0);
tesseract::ResultIterator* ri = api->GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_TEXTLINE;
if (ri != 0) {
do {
const char* line = ri->GetUTF8Text(level);
float conf = ri->Confidence(level);
int x1, y1, x2, y2;
ri->BoundingBox(level, &x1, &y1, &x2, &y2);
printf("line: '%s' %d %d %d %d;\n",line, x1, y1, x2, y2);
* // get each word in the "line"*
delete[] line;
} while (ri->Next(level));
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
---
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].
For more options, visit https://groups.google.com/groups/opt_out.
