Consider an example as shown below:

alt text

I ran imageProcess and I fail to get C (I also get a false positive "J", but this is okay). In some other images there are more true negatives. In general, is there any easy way to deal with this kind of image? If not, can I make the OCR more lenient so that I increase recall rate (sacrificing precision)?

asked 14 Dec '14, 05:04

seominjoon's gravatar image

seominjoon
111


Hi! This issue was fixed by our developers and now the fix is finally available in Cloud OCR SDK. We also recommend you to increase the scanning resolution to improve the recognition result.

link

answered 09 Feb '15, 19:09

Anna%20Falevskaya's gravatar image

Anna Falevskaya ♦♦
715

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:

×1
×1
×1

Asked: 14 Dec '14, 05:04

Seen: 642 times

Last updated: 09 Feb '15, 19:09

Related questions

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