Is it possible to set a "clipping window" for recognition process, if I know the area of interest for me?

asked 25 Sep '13, 19:15

als2002's gravatar image

als2002
34

converted 25 Sep '13, 20:38

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦
790112


You can always crop your image on your side and pass it to the processImage method.

Also if the region you want to recognize contains the text only, you can use the processTextField method and specify the coordinates in its region parameter.

link
This answer is marked "community wiki".

answered 25 Sep '13, 20:44

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦
790112

wikified 25 Sep '13, 20:44

Well, it is relatively easy to crop single page .png file ( in my case ), but can be tricky enough for multi-page .pdf.
processTextField (as far as I can understand from documentation)is well suited for single-value field record, and will not retain text's geometry...

(26 Sep '13, 13:38) als2002

In ABBYY FineReader Engine it is also easy to do by adding text blocks manually. This feature is not implemented in ABBYY Cloud OCR SDK.

(01 Oct '13, 13:17) 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

By RSS:

Answers

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

Tags:

×195
×106
×31
×3

Asked: 25 Sep '13, 19:15

Seen: 1,710 times

Last updated: 01 Oct '13, 13:17

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