I am trying to get back OCR xml output that has been deskewed.

My application maps the OCR data to an image. Currently I am getting back both pdfsearchable and xml output. The pdfsearchable is then converted to an image by my application. As far as I know I cant get back an image file, so I am taking the pdfsearchable output and rendering it to an image file on my end. This works fine for getting a deskewed image of the document, however the xml output appears to reflect the original skew.

asked 21 Mar '14, 17:15

X-uarg%20G-raux's gravatar image

X-uarg G-raux

edited 07 Apr '14, 17:25

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦

Sorry for the long delay. In Cloud OCR SDK there is no way to get coordinates on the deskewed image directly. To get it, you can send the deskewed image for re-recognition, but, unfortunately, it will be charged once again.


answered 07 Apr '14, 17:29

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦

Anastasia, can this feature be implemented in future? I need this feature too!

(05 May '14, 21:08) Vitalie

Vitalie, X-uarg G-raux, can you please specify whether you need both coordinated of deskewed and nondeskewed image? Or you need only deskewed one?

(18 Jun '14, 11:22) SDK_support ♦♦
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: 21 Mar '14, 17:15

Seen: 929 times

Last updated: 18 Jun '14, 11:22

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