Script Classification and Writer Identification: Two Tasks for a Common Understanding of Cultural Heritage - Dataset

Writer identification and Script classification are usually considered as two separated and very different tasks, as well in palaeography as in computer science. Following the ICDAR competition on the CLAMM corpus about script classification and dating, this dataset provides the output created by running two infrastructures created for Script classification at a large scale (medieval scripts) on a more homogeneous dataset with a focus on Writer Identification.

If you use the present repository, its data and figures, please consult and cite:

Stutzmann, Dominique, Christopher Tensmeyer, and Vincent Christlein. « Writer Identification and Script Classification: Two Tasks for a Common Understanding of Cultural Heritage ». manuscript cultures, 15 (2020): 11-24. https://www.csmc.uni-hamburg.de/publications/mc/files/articles/mc15-02-stutzmann.pdf