Dioscorus case study

The archive of Dioscorus of Aphrodito (6th c. A.D.) is the richest papyrus archive of the Byzantine period. Gathering more than 700 texts of various content, it provides a unique opportunity to study day-to-day cursive writing and literacy in the microcosm of an Egyptian village.

From the Dioscorus archive was selected a dataset specially tailored for the task of Writer Identification, see GRK-Papyri

An extension of GRK-Papyri from 50 to 120 papyri was segmented into rows to form the Papy-Row dataset (accessible here) and presented during the PatReCH workshop in ICPR 2020, see here.

GRK-Papyri is used in the following publications:

  • Nasir S., Siddiqi I., Moetesum M. (2021) "Writer Characterization from Handwriting on Papyri Using Multi-step Feature Learning". In: Barney Smith E.H., Pal U. (eds) Document Analysis and Recognition – ICDAR 2021 Workshops. ICDAR 2021. Lecture Notes in Computer Science, vol 12916. Access here.
  • Nasir S., Siddiqi I. (2021) "Learning Features for Writer Identification from Handwriting on Papyri". In: Djeddi C., Kessentini Y., Siddiqi I., Jmaiel M. (eds) Pattern Recognition and Artificial Intelligence. MedPRAI 2020. Communications in Computer and Information Science, vol 1322. Access here.
  • Christlein V., Marthot-Santaniello I., Mayr M., Nicolaou A. and Seuret M., "Writer Retrieval and Writer Identification in Greek Papyri“ (forthcoming in the Proceedings of IGS 2021). See video 18 on this page from Neo-Paleography Conference

Sidra Nasir, "Identification of Scribes from Historical Manuscripts", Masters thesis in Computer Science defended in April 2021 at Bahria University, Islamabad, downloadable here.