Support for Running or Attached Scripts...?!?!?!

[YogiYang]

I want to know if it would be possible to OCR Indic Languages as most of the languages are based on Sanskrit or Devnagri and thus each character is attached with a line on top unlike english alphabet where every character is separate.

Would this OCR Engine work with Indic Script. I am not able to get it to work so if there are any work around please do help implement those so that I can evaluate it better.

TIA

Yogi Yang

[Loïc]

Hi the list of supported language are defined on the TesseractDictionary enumeration.

You can get it from this link: https://www.gdpicture.com/guides/gdpicture/v5/gdpictur ... DoOCR.html

Today, 10 languages are supported:

0: German.
1: Fraktur.
2: English.
3: French.
4: Italian.
5: Dutch.
6: Portuguese.
7: Spanish.
8: Vietnamese.
9: Polish.


Unfortunately nothing yet for Indic Script.

Best regards,

Loïc

[YogiYang]

NO support for Indic Scripts. That is bad news for me.

Are there any ways to train Tesseract to understand and recognize IndicScript? Can someone do some hand holding here please.

TIA

Yogi Yang