International Conference on Document Analysis and Recognition
This paper approaches manuscript dating from a Bayesian perspective. Prior work on paleographic date recovery has generally sought to predict a single date for a manuscript. Bayesian analysis makes it possible to estimate a probability distribution that varies with respect to time. This in turn enables a number of alternative analyses that may be of more use to practitioners. For example, it may be useful to identify a range of years that will include a document’s creation date with a particular confidence level. The methods are demonstrated on a selection of Syriac documents created prior to 1300 CE.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
“Licensed to Smith College and distributed CC-BY under the Smith College Faculty Open Access Policy.”
Howe, Nicholas and Xie, Stephanie, "Chronological Profiling for Paleography" (2017). Computer Science: Faculty Publications, Smith College, Northampton, MA.