This repository contains the web front-end of the web application presented in the article:

Dencker, T., Klinkisch, P., Maul, S. M., and Ommer, B. (2020): Deep Learning of Cuneiform Sign Detection with Weak Supervision using Transliteration Alignment, PLOS ONE, 15:12, pp. 1–21

The web front-end offers the following functionality:

The web front-end has been developed using a combination of PHP and JavaScript.



1) Create a copy of this repository on your machine so that the installed web server makes the web front end available through the browser.

2) Ensure that the cuneiformbrowser/data and cuneiformbrowser/log directory is writable. One of several options is to use the chmod command, e.g. $chmod -R 777 ./cuneiformbrowser/log/

3) Setup your login preferences under cuneiformbrowser/users/users.xml. (WARNING: the user access management is very basic and only provides a low level of protection)

4) To enable sign detection in the web front end, install the cuneiform-sign-detection-code on the same machine and run the webapp back-end using $python For instruction how to run the webapp back-end, refer to the readme provided in ./lib/webapp/.


Please refer to the video and the help texts provided throughout the web front-end.

Web interface detection


The two example images of clay tablets included in this repo are from the collection of the Vorderasiatisches Museum Berlin which kindly granted us permission to use them for our research purposes.