uchicago-digitalculture-webdev/deepscribe

Code and sample images described in the paper "DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning"

35
/ 100
Emerging

This tool helps researchers in ancient Near Eastern studies automatically identify and classify Elamite cuneiform signs on images of ancient tablets. It takes scanned images of Persepolis Fortification Tablets as input and outputs a proposed transliteration of the cuneiform text, assisting in the daunting task of deciphering and analyzing these historical documents. It is designed for epigraphers, archaeologists, and historians specializing in the Achaemenid Empire.

No commits in the last 6 months.

Use this if you need to rapidly process and transliterate a large collection of Elamite cuneiform tablet images, or want to explore automated assistance for decipherment.

Not ideal if you are working with cuneiform scripts other than Elamite, or if your primary interest is in developing new deep learning architectures from scratch rather than applying existing ones.

ancient-history epigraphy archaeology cuneiform-studies digital-humanities
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Dec 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uchicago-digitalculture-webdev/deepscribe"

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