I have a sample Cheque. I am trying to read the following
a) Branch Name (i.e. Salwa Branch)
b) Doha on (i.e. 1/7/2016)
c) Pay against this cheque to/order
d) Riyals
e) QR
f) Cheque No.
I am using Tesseract. What extra thing I need to do for getting the relevant info since I am not able to get the informations properly.
Or any other OCR SDK is there specific to this purpose...Please help
Thanks in advance.
2 Answers
Answers 1
Everything that is hand written, will not be accepted in any way. You have only chances with known or similar fonts. In your case i would analyse the complete image/tiff and than go through all blocks that are created with Tesseract.
Answers 2
is easy with tesseract.
Use this .net wrapper works very well.
https://www.nuget.org/packages/Tesseract/
Examples can be found on his project page.
In same cases you have to train the fonts. How you can read here:
http://www.joyofdata.de/blog/a-guide-on-ocr-with-tesseract-3-03/
For Number and symbols (middle bottom) is a trained font available I found by google for tesseract.
0 comments:
Post a Comment