JPLeoRX/detectron2-publaynet

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

39
/ 100
Emerging

This project provides pre-trained models that automatically identify and categorize different elements within research papers and articles. You can input scanned or digital research paper images, and it will output bounding boxes and labels for elements like text paragraphs, lists, figures, and tables. This is ideal for researchers, librarians, or data scientists working with large collections of academic documents.

No commits in the last 6 months.

Use this if you need to quickly and accurately extract the structural layout of academic papers to automate tasks like data extraction, archiving, or content analysis.

Not ideal if you need to analyze highly specialized document types outside of academic papers or require very high precision for extremely nuanced layout elements.

document-analysis academic-research information-extraction digital-libraries content-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

50

Forks

8

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/JPLeoRX/detectron2-publaynet"

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