Hello, I have a quick question based on your past experience.

I have a product where I am in control of the form that I will be later processing with your product. Therefore, I have the opportunity to select among the field marking types that are listed here:

http://ocrsdk.com/documentation/specifications/field-marking/

My question is, in your experience, which of these field types generally produces the highest quality results? I've tried a few with very mixed quality and would like to maximize the possibility of getting a high quality result.

asked 22 Aug '12, 05:06

dante's gravatar image

dante
376

edited 01 Oct '12, 09:36

Vasily%20Panferov's gravatar image

Vasily Panferov ♦♦
5422516


Hello!

Preferable marking type is 'greyBoxes'. It gives the least amount of artifacts during binarization, a process of making bi-tonal image used by recognizer.

An alternative to gray boxes is boxes with 'dotted' borders. It is not presented in API yet but 'simpleText' type can be used instead. In case of 'dotted' borders they will be removed by de-speckling filter before recognition.

Best regards, Dmitry.

link

answered 22 Aug '12, 12:21

Chudik79's gravatar image

Chudik79
692

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:

×17
×3

Asked: 22 Aug '12, 05:06

Seen: 1,550 times

Last updated: 01 Oct '12, 09:36

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