Hi,
I have this code which gives me confidence level of each character in a
word. Now if I have multiple words in a image it gives me confidence level
of each character.
But the problem is it prints all in a sequence (It is not taking empty
space ) how do I identify that a word ends here and the other word's
character probability starts. Any help on this ???
For example: If my image has Book Now (refer attached image) My current
output is as follows. Now I want to introduce a delimiter after symbol "K"
then how should I do that. So that I will know that till Symbol K it is one
word and after that it is another word.
sample output:
symbol B, conf: 95.727936 - B conf: 95.727936
- 3 conf: 83.558624
- E conf: 81.664284
---------------------------------------------
symbol O, conf: 90.067154 - O conf: 90.067154
- 0 conf: 87.427773
- Q conf: 83.844460
- C conf: 82.962616
- G conf: 79.682472
---------------------------------------------
symbol O, conf: 90.468826 - O conf: 90.468826
- 0 conf: 87.815132
- C conf: 86.248314
- Q conf: 82.877472
---------------------------------------------
symbol K, conf: 93.121216 - K conf: 93.121216
---------------------------------------------
symbol N, conf: 91.598183 - N conf: 91.598183
---------------------------------------------
symbol O, conf: 89.931847 - O conf: 89.931847
- 0 conf: 87.237823
- Q conf: 84.576927
- C conf: 82.600273
- G conf: 80.553169
- D conf: 79.337044
---------------------------------------------
symbol W, conf: 96.001007 - W conf: 96.001007
- w conf: 86.990593
---------------------------------------------
#include <tesseract/baseapi.h>
#include <leptonica/allheaders.h>
#include </usr/local/include/tesseract/pageiterator.h>
#include </usr/local/include/tesseract/resultiterator.h>
#include <iostream>
int main()
{
Pix *image = pixRead("sample.png");
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)));
}
}
--
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 post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/9a1767c5-226a-460d-ad85-545313fd5bb0%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
