Hi. How can I perform word-level recognition? For now when I try to recognize document (output format - XML) I get chars positions. But I need to get words positions.


asked 25 Nov '13, 13:04

Gennadiy%20Krol's gravatar image

Gennadiy Krol

Could you please specify the product you use?

(26 Nov '13, 14:59) Anastasia Ga... ♦♦

Abbyy OCR cloud service

(26 Nov '13, 15:00) Gennadiy Krol

Unfortunately, this feature is not implemented in Cloud OCR SDK. You can calculate word coordinates on your side using the char coordinates. The "wordStart" character attribute could be helpful: it is true when the character is first in a word.


answered 26 Nov '13, 15:33

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦

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: 25 Nov '13, 13:04

Seen: 1,664 times

Last updated: 26 Nov '13, 15:33

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