muhd-umer/pyramidtabnet

Official PyTorch implementation of PyramidTabNet: Transformer-based Table Recognition in Image-based Documents

30
/ 100
Emerging

PyramidTabNet helps you automatically extract structured table data from scanned documents, images, and PDFs. It takes an image-based document containing tables as input and precisely identifies the tables and their internal structure (rows and columns). This is ideal for data entry specialists, researchers, and operations teams who need to convert visual table information into an editable, structured format for analysis or database entry.

No commits in the last 6 months.

Use this if you need to accurately detect tables and understand their layout in various image-based documents, saving significant manual data entry time.

Not ideal if your documents are already in a structured, machine-readable format like Excel or CSV, or if you only need to extract plain text without table recognition.

document-automation data-extraction digitization information-capture document-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

28

Forks

2

Language

Python

License

MIT

Last pushed

Oct 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/muhd-umer/pyramidtabnet"

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