Hello together,
I have multiple PDFs from which I want to extract data using ABBYY FlexiCapture. Since all PDFs have the same structure, I used the Document Definition Editor within the Project Station to create a layout. Now my question: Is it possible to enhance character recognition for these Document Definitions without ABBYY FlexiCapture for Invoices? This would be very helpful as many 0s are recognized as 9s and verifying every document is not a feasible Option.
Thank you for your help!
Comments
3 comments
Hello,
There are many causes that may result in poor characters' recognition, so could you please send us some sample images for further investigation of what happened in your case.
Taking this as an example:
I have an AutoCorrect-Script set up to remove the dots and divide the resulting integer by 100.
ABBYY treats the 2s as 7s:
Hello,
Sorry, we cannot reproduce the issue on this provided small sample (when we have placed it on the A4 mock-up document all digits were recognized correctly). We suppose that we will be able to reproduce it if we get whole image, not the part. Could you send us the original images and, if it is possible, your project?
Please sign in to leave a comment.