I'd like to know if it´s possilbe to use trainning in the SDK. How can i use training in Cloud SDK ?


asked 12 Apr '12, 22:34

andrepersilva's gravatar image


edited 13 Apr '12, 11:50

Nikolay_Kh's gravatar image

Nikolay_Kh ♦♦

Can you please be more specific with your task? Why would you need training? Do you want to use OCR for some special characters or not supported language?

(13 Apr '12, 11:47) Nikolay_Kh ♦♦

ABBYY Cloud OCR SDK does not support custom font training. There is ABBYY FineReader Engine that supports it, but this is traditional SDK, not cloud. You can check it out here: http://www.abbyy.com/ocr_sdk/


answered 14 Apr '12, 01:03

Andrey%20Isaev's gravatar image

Andrey Isaev ♦♦

The Addby Finner Renner some characters are not identified or changed by ocr, some example / changed by *. If I used by Desktop Reader the precision 70% but I'm training and recognize is high tax 97%. I need precision closed 95%. If It isn´t possible by Cloud I think so used by SDK by Desktop. I think the problem not language but It's font.


answered 13 Apr '12, 23:22

andrepersilva's gravatar image


Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here



Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "title")
  • image?![alt text](/path/img.jpg "title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported



Asked: 12 Apr '12, 22:34

Seen: 2,981 times

Last updated: 14 Apr '12, 01:03

© 2016 ABBYY. All rights Reserved. www.ABBYY.com | Privacy Policy | Legal