Question
Fetch the data from scanned image file either Digital or Hand written
Hi Team,
I have a requirement in Pega Robotics to read/fetch the details from scanned image pdf file but in this file contains both hand written things and digital also.
as i figured out IBM Datacap application and Abbyy flexicapture contains the ICR capability. Request you to help me in configuring Ibm datacap and Abbyy flexi capture with Pega Robotics/PegaBpm.
if i want to buy IBM Datacap application liscence and i implemented the solution in IBM datacap then how to integrate with IBM datacap and Pega robotics/Pega BPM. if there is a way, can you please guide us what infrastructure need to setup my side.
if i want to buy Abbyy flexicapture product liscence and i implemented the solution in Abbyy flexicapture then how to integrate with abbyy flexicapture and Pega robotics/Pega BPM. if there is a way, can you please guide us what infrastructure need to setup my side.
and if i want use any one of the above tools, which tool more advantages and more accuracy.
Thank you!
Regards,
Madhu Balineni.
***Moderator Edit-Vidyaranjan: Updated Platform Capability***
Hi Jef,
Thank you very much for your response!!!
Yes you are correct when we use DocumentOcr for digital scanned pdf it will give text but in my current documents contains the check boxes and radio button are there and it is giving some junk data.
can you please suggest what steps need to take care of this scenario.
Thank you!
Regards,
Madhu Balineni.
The new functionality will allow you to resolve this. I don't have a release date that yet, but it is coming soon. With this new functionality you would choose the Include Images option in DocumentOCR and then you would read the checkboxes using Optical Mark Recognition in the the PDF Connector. I will update this thread when the new features are released.
Hi Jef,
Thank you for your response!!
Please let me know once new functionality is released.
Thank you!
Regards,
Madhu Balineni.
Hi Jef,
Any update please?
Have you tried using our DocumentOCR component? This will convert the digital text in an OCR document to text that may be manipulated with the PDF Connector.
We are adding new PDF functionality soon that will make working with PDF files much easier. This will include the ability to use Optical Mark Recognition to determine if an document has hand written check marks or signatures.
I will post some examples here when this functionality is released. Check the build notes as well for release information.