Imaging Science Ph.D. Thesis Defense: Anna Starynska
Ph.D. Thesis Defense
Palimpsest text restoration in historical manuscripts using deep learning methods
Anna Starynska
Imaging Science PhD Candidate
Chester F. Carlson Center for Imaging Science, RIT
Abstract: Historical palimpsests are manuscripts that have several layers of text overwritten one over another, where the previous text is erased. For many centuries palimpsest text of ancient manuscripts was considered impossible to recover. Nowadays, with new technology, such as multispectral imaging, under some portion of Electro-Magnetic spectrum illumination, the overwritten text can become visible again. This peculiar property of faded ink and some traditional signal processing methods (PCA, ICA, etc.) had already helped recover numerous manuscripts. Nevertheless, even showing the best performance, existing methods can only enhance the visibility of the text but not be able to eliminate the effects of occlusion from the overlapping text, stains, and fading of aged parchment. The dependency of these methods' performance on material variation, caused by aging, ink composition, and the text-erasing process is not well understood. It makes their performance very inconsistent and parameter tuning very labor-intensive. As a solution to this, we suggest reconstructing the palimpsest text using deep neural networks that have already proved themselves as the leading technology in the field of image reconstruction, in-painting, and super-resolution. Additionally, we present a method that combines spectral information from a multispectral imaging system with spatial statistics of palimpsest text. Advisor- Dr. David Messinger
Intended Audience: Undergraduates, graduates, and experts. Those with interest in the topic.
To request an interpreter, please visit https://myaccess.rit.edu
Event Snapshot
When and Where
Who
Open to the Public
Interpreter Requested?
No