Search code examples
azure-cognitive-servicesazure-form-recognizer

Extract text from required pages in PDF file


I am trying to use Form Recognizer - Azure cognitive service to extract text from pdf file. I am using custom model where by I train this service with my model and then try extracting data.

My PDF usually has more than 1 pages. But i am interested in extracting text from first page. Rest all pages does not have any importance.

So is there any way where I train my system to extract text from selected pages by giving page number?

Regards,

Madhu


Solution

  • The Form Recognizer API currently does not support page ranges for documents when training models. You might have to pre-process the document using 3rd party tools/APIs to only send the pages you need the model to be trained with.