So I need to recognize receipts from restaurants and pull the total out to operate on it. I only am concerned with the numbers on the receipt, so I am trying to figure out the best way to do this. I am currently just using processImage and getting all the text back and running it through a regex to pull out the numbers and then the total. But I want to figure out if I can use processTextField instead, since I am only concerned with a small amount of text and since processTextField is much cheaper. But I also don't want to loose to much accuracy and I can't specify a region easily, so it would still be best to process the whole picture. Any helpful suggestions?

Thanks for the help.

asked 15 Jan '13, 05:15

tLewis's gravatar image

tLewis
112

edited 15 Jan '13, 12:49

Andrey%20Isaev's gravatar image

Andrey Isaev ♦♦
2835


processFields is good when the whole picture is small or you need to recognize only part of large image with predefined coordinates. Since total amount can be anywhere on the receipt, you should recognize whole image anyway to find total. So it looks like what you do now is optimal solution.

link

answered 15 Jan '13, 09:33

Andrey%20Isaev's gravatar image

Andrey Isaev ♦♦
2835

I thought you might say that, but I was hoping you would not. I was hoping I might be able to tune processFields in order to suit my needs, as it is more economically feasible and since I need such a small amount of information, but I suppose processImage would still be the best way to do it.

(15 Jan '13, 18:44) tLewis
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:

×42
×24
×9
×4

Asked: 15 Jan '13, 05:15

Seen: 2,063 times

Last updated: 15 Jan '13, 18:44

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