I am trying to OCR a rather large (not in file size) image file of "tabulated" numbers. I ultimately want to import it in to Excel and make a surface plot (the numbers actually refer to land heights).

The image itself is 2978 x 4000 pixels and is only 294kB in size being a two colour png image file.

The two digit numbers are uniformly arranged in virtual columns and rows (there are no grid lines however) making the virtual table approximately 250x186 cells in size.

Are there any issues that I may have with trying to OCR a file/table of this size?



asked 10 Nov '15, 08:22

Bull's gravatar image


I`m not official from ABBYY, just simple user of OCRSDK. By our experience we successfuly process images bigger that 3000x4000 pixels containing table data. Note this info from OCRSDK documentation: "With ABBYY Cloud OCR SDK you cannot open images larger than 32512*32512 pixels." So I think you can process your images.

(10 Nov '15, 16:10) Vitalie

Vitalie, thank you for the comment!

Bull, you also can share your image sample or send it to CloudOCRSDK@abbyy.com and we will test it.

(11 Nov '15, 11:39) Oksana Serdyuk ♦♦

OK thanks for the tips. File sent.

(12 Nov '15, 11:56) Bull
Be the first one to answer this question!
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: 10 Nov '15, 08:22

Seen: 1,316 times

Last updated: 12 Nov '15, 12:02

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