Classify PDF with only few relevant pages

Help Activities
, ,
1

Hello,
I am using Machine Learning Classifier, inside Classify Document Scope trying to classify documents to my DU process.
My ML Classifier have two documents as option, alsoin the Taxonomy of the procees only this two documents type existing.
I am facing two problems -

  1. PDF with 100+ pages, that i have only two pages inside the that are the relevant doc type i need to extract data from, all other pages are different documents inside the PDF file. i want to somehow get only the 2-4 relevant pages.

  2. PDF files that arriving to the classifier but they are not one of the doc types, they are different doc types that i do not need to extract anything from them, can i somehow define that they will be classify as “other” maybe?

many thanks everyone!