asagar60/TableNet-pytorch

Pytorch Implementation of TableNet

44
/ 100
Emerging

This project helps you automatically extract structured data from tables found within images or scanned documents. It takes an image containing a table as input and outputs the identified table's location, its column structure, and the text content of each cell, making it easy to convert visual information into usable data. This is ideal for data entry specialists, researchers, or anyone needing to digitize information locked in image-based tables.

No commits in the last 6 months.

Use this if you need to reliably extract data from tables embedded in images, like scanned reports or screenshots, and convert it into a structured, editable format.

Not ideal if your tables are already in digital, editable formats like PDFs where text is selectable, or if you only need to identify the presence of a table without extracting its full structure and content.

data-extraction document-digitization information-capture data-entry-automation research-data-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

66

Forks

24

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 21, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/asagar60/TableNet-pytorch"

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