CaseDrive/publaynet-models

Trained Detectron2 object detection models for document layout analysis based on PubLayNet dataset

29
/ 100
Experimental

This project offers pre-trained models that can automatically analyze the layout of research papers and articles. You input an image of a document page, and it identifies and outlines distinct elements like text blocks, lists, figures, and tables. This is ideal for researchers, librarians, or data scientists working with large collections of academic papers who need to extract or categorize content based on its visual structure.

No commits in the last 6 months.

Use this if you need to automatically identify and categorize different layout elements (text, figures, lists) within scanned or digitized research papers.

Not ideal if your primary goal is to extract the actual text content (OCR) without needing to understand the document's visual structure.

document-analysis academic-publishing research-data-extraction information-retrieval digital-libraries
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

29

Forks

2

Language

Python

License

Last pushed

Apr 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CaseDrive/publaynet-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.