Contrastive Attention Networks for Attribution of Early Modern Print
This addresses the challenge for historians and bibliographers in attributing anonymously printed books, offering an automated tool to replace manual investigations, though it is incremental in applying existing ML techniques to a new domain.
The paper tackles the problem of identifying unknown printers in early modern English printed books by matching damaged character type-imprints, using a Contrastive Attention-based Metric Learning approach with synthetic data to improve matching accuracy, as validated by human experts on two philosophical works.
In this paper, we develop machine learning techniques to identify unknown printers in early modern (c.~1500--1800) English printed books. Specifically, we focus on matching uniquely damaged character type-imprints in anonymously printed books to works with known printers in order to provide evidence of their origins. Until now, this work has been limited to manual investigations by analytical bibliographers. We present a Contrastive Attention-based Metric Learning approach to identify similar damage across character image pairs, which is sensitive to very subtle differences in glyph shapes, yet robust to various confounding sources of noise associated with digitized historical books. To overcome the scarce amount of supervised data, we design a random data synthesis procedure that aims to simulate bends, fractures, and inking variations induced by the early printing process. Our method successfully improves downstream damaged type-imprint matching among printed works from this period, as validated by in-domain human experts. The results of our approach on two important philosophical works from the Early Modern period demonstrate potential to extend the extant historical research about the origins and content of these books.