Thursday, April 25, 2024

 



"Funded through two grants from The Andrew W. Mellon Foundation, Phase One of the Open Islamicate Texts Initiative Arabic-script OCR Catalyst Project (OpenITI AOCP) is the first undertaking of its kind to tackle the technical and organizational barriers that historically have stymied the development of Arabic-script OCR and digital text production for Islamicate Studies.
OpenITI AOCP is led by an interdisciplinary team of humanities, computer science, and digital humanities co-principal investigators from Roshan Institute for Persian Studies at the University of Maryland, College Park, Northeastern University’s NULab for Texts, Maps, and Networks, the Aga Khan University’s Institute for the Study of Muslim Civilisations in London, and the Maryland Institute for Technology in the Humanities at the University of Maryland, College Park. We are proud to partner with the SHARIAsource project of the Program in Islamic Law at Harvard Law School and the eScripta project of Universit√© Paris Sciences et Lettres for the technical development portion of the project.

The primary technical goal of the first phase of OpenITI AOCP is to achieve ≥97% character accuracy rates (CARs) for OCR on the most used Persian and Arabic print typefaces. 

The second major deliverable of OpenITI AOCP is an open-source and user-friendly digital text production pipeline for Persian and Arabic texts."


No comments:

Post a Comment