Question

nonaccurate OCR results from Abbyy finereader

Pega 8.1.1

OCR applied to pdf documents through Abby Fine reader is not giving back accurate text, especially pdfs that contain rotated pdfs.

I have attached an example of some of the results we get back when uploading a pdf.

Another example is "I" is often misrecognized as a "1".

***Edited by Moderator Marissa to update platform capability tags; update SR Details****

Group Tags

Comments

Keep up to date on this post and subscribe to comments

Pega
December 10, 2019 - 7:03am

Dear Rawan,
Please double check if you're using the latest version of the Pega OCR component. 
Where there are by default turned on parameters responsible for correcting orientation and skew. 

Nevertheless please keep in mind that the engine which is used is not able to perform accurate table analysis. In your example there are a lot of tables from which extracted text will not be in an order you may expect. 

Mentioned wrong recognition can be related to the quality of processed file or you may not have some fonts installed on your server. Have you installed fonts during engine installation?

Best regards
Mariusz

December 30, 2019 - 11:57am
Response to grabm

Hi Mariuz,

Yes we are using the latest version of Pega OCR, but still having issues with the orientation and skew.

Thanks you