biswassanket/DocSegTr

A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers

38
/ 100
Emerging

This project helps researchers and academics automatically understand the structure of scientific papers. It takes an image of a document page and outputs a precise map of distinct content areas like text blocks, figures, and tables. This tool is designed for anyone needing to analyze or extract specific sections from academic documents.

No commits in the last 6 months.

Use this if you need to programmatically identify and separate different logical components within document images, such as for content extraction or layout analysis.

Not ideal if you are looking for a simple, off-the-shelf application or web tool without needing to engage in a technical setup.

academic-publishing document-analysis research-automation information-extraction digital-libraries
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

59

Forks

8

Language

Python

License

GPL-3.0

Last pushed

Sep 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/biswassanket/DocSegTr"

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