Who Printed Milton's Tetrachordon (1645)?

Achinstein, Sharon; Burton, Benjamin Robert

doi:10.1093/library/14.1.18

Cited by 4 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Essentially, once a metallic type piece is damaged, whether by being dropped on the ground, warped under pressure, or some other means, the type-imprints produced by the type piece become unique like a fingerprint as illustrated in Figure 2 and the top of Figure 3. Manual forensic analyses of these most distinctive aberration patterns-bends and fractures, as well as other tell-tale cues identified by bibliographers, have produced evidence connecting anonymously printed works with known printers (Weiss 1992;van den Berg and Howard 2004;Achinstein and Burton 2013;Garrett 2014;Bricker 2016;Lavin 1972;Adams 2010;Como 2012). For example, Charlton Hinman's pioneering work in the 1960s exhaustively compared all letterforms across 55 copies of Shakespeare's First Folio using careful notetaking methods to uncover the collation process (Turner 1966;Hinman 1963).…”

Section: Early Modern Print and Damaged Type Piecesmentioning

confidence: 99%

Contrastive Attention Networks for Attribution of Early Modern Print

Vogler

Goyal

Reddy

et al. 2023

AAAI

View full text Add to dashboard Cite

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.

show abstract