How does Adobe Acrobat PDF Extract API identify document structure?

[sathish_8925]

Hi Team,

I’d like to understand how the Adobe Acrobat PDF Extract API identifies the structure of a PDF document.
Does it rely on OCR-based detection, or does it use other layout or heuristic-based methods for identifying elements such as paragraphs, lists, tables, and headings?

Could you please share some insights or documentation references about how the API determines and classifies these structural elements?

Thanks,
Sathish

[Joel Geraci · Accepted solution]

It uses AI rather than heuristic-based methods. We train it on literally millions of PDF files. Generally, it extracts the text from the PDF and will only OCR a document when the PDF is image-only.

[sathish_8925]

Hey @Joel Geraci , Thanks for the reply.