How Adobe Desktop PDF Editor auto tag works internally ?

Question

Hi Team,I’d like to understand how the Adobe Acrobat Desktop PDF Editor Autotag works internally to 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

AnandSri · Accepted Answer

Hello @9896408

I hope you are doing well, and thank you for reaching out.

Adobe’s Autotag feature in Acrobat Desktop is designed to make PDFs accessible by adding a logical structure tree, but the process is more heuristic-driven than purely OCR-based.

Autotag analyzes the existing PDF content stream and layout rather than relying solely on OCR. It looks at:

Text objects and font attributes (size, weight, style) to infer headings vs. body text.
Reading order and positioning to group paragraphs and identify lists.
Graphic elements and bounding boxes for tables, figures, and images.

To learn more, please see these Adobe articles:

Create and verify PDF accessibility (Acrobat Pro).

Creating accessible PDFs.

Regards,

Anand Sri.

Sign up

To post, reply, or follow discussions, please sign in with your Adobe ID.

Sign in to Adobe Community

To post, reply, or follow discussions, please sign in with your Adobe ID.

Scanning file for viruses.

This file cannot be downloaded