How to call and limit tesseract characters into 4 Letters only in c#?

Question

Is it possible to limit recognition of tesseract to four characters only like this "abcdABCD" ? I've tried this link and created a ".cfg" file inside of my folder TESSDATA which is inside of my project folder.

C:\Users\Julian Concepcion\Desktop\MyProject\MyProject\tessdata

it is named config.cfg, inside the config.cfg is this "tessedit_char_whitelist abcdABCD " but I don't know how to use it inside the c#. This is how I call my tesseract

tess = new Tesseract("C:\\Users\\Julian Concepcion\\Desktop\\MyProject\\MyProject\\tessdata", "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED);

score 0 · Answer 1 · answered Feb 11 '14 at 23:50

0

Do just like that link suggested:

tesseract->SetVariable("tessedit_char_whitelist", "abcdABCD");

No need to create any config file.

answered Feb 11 '14 at 23:50

nguyenq

8,212
1
16
16

@nquyenq - It doesn't work. I tried this `tess.SetVariable("tessedit_char_whitelist", "abcdABCD");` – julianconcepcion Feb 13 '14 at 18:30
@nquyenq - still, it recognize other characters – julianconcepcion Feb 13 '14 at 18:31
Did you call it after the `init` method? – nguyenq Feb 14 '14 at 00:42

How to call and limit tesseract characters into 4 Letters only in c#?

1 Answers1