Research Description
MEDIEVAL LATIN MANUSCRIPTS
The team is in the process of curating a dataset of Latin Biblical manuscripts, exploring the experimental possibilities offered by the utilization of images from various manuscripts reproducing the same biblical text (the beginning of Genesis and the Gospel of Matthew). The dataset encompasses over 400 pages written by nine distinct scribes. The primary objective is to investigate the effectiveness of modern deep learning architectures, employing diverse training set dimensions and utilizing various pre-processing techniques to evaluate the performance and capabilities of the models utilized.
GREEK AUTOGRAPH PAPYRI
The project's initial objective is to select autograph Greek papyri that can be securely dated and originate from archives spanning various periods, from the Ptolemaic to the Arab period. These selected papyri will be closely examined from a paleographic, grammatical, lexical, and bibliological perspective in an attempt to identify specific characteristics attributable to the scribes who produced them and/or the period in which they were written. Secondly, the findings of this study will be incorporated into artificial intelligence (AI) systems to enable them to identify and date similar texts
