Contrastive Attention Networks for Attribution of Early Modern Print

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.

Authors

• Nikolai Vogler UC San Diego
• Kartik Goyal Toyota Technological Institute at Chicago
• Kishore PV Reddy UC San Diego
• Elizaveta Pertseva UC San Diego
• Samuel V. Lemley Carnegie Mellon University
• Christopher N. Warren Carnegie Mellon University
• Max G'Sell Carnegie Mellon University
• Taylor Berg-Kirkpatrick UC San Diego

Keywords

• APP: Humanities & Computational Social Science
• CV: Image and Video Retrieval
• ML: Applications