Deep Learning Approaches to Classification of Production Technology for 19th Century Books
This work addresses a specific challenge in cultural research for historians and digital humanities scholars, but it is incremental as it applies existing methods to a new dataset with limited success.
The paper tackled the problem of classifying production technology for 19th-century book illustrations, such as wood/copper engraving vs. lithography, using deep learning, but achieved only around 70% accuracy, which is low and comparable to human performance.
Cultural research is dedicated to understanding the processes of knowledge dissemination and the social and technological practices in the book industry. Research on children books in the 19th century can be supported by computer systems. Specifically, the advances in digital image processing seem to offer great opportunities for analyzing and quantifying the visual components in the books. The production technology for illustrations in books in the 19th century was characterized by a shift from wood or copper engraving to lithography. We report classification experiments which intend to classify images based on the production technology. For a classification task that is also difficult for humans, the classification quality reaches only around 70%. We analyze some further error sources and identify reasons for the low performance.