Supervised vs. unsupervised deep learning for medieval Hebrew manuscripts

Daria Vasyutinsky Shapira, Irina Rabaev, Reem Alaasam, Jihad El-Sana

Abstract: Paleographical features can be extracted from digitized images by applying deep machine learning. This paper presents an unsupervised deep-learning method for determining script types and modes for medieval Hebrew manuscripts. The results would be presented vs. the previously published results of supervised deep learning for the same datasets.