Optical character recognition (OCR) has proved a powerful tool for the digital analysis of printed historical documents. However, its ability to localize and identify individual glyphs is challenged by the tremendous variety in historical type design, the physicality of the printing process, and the state of conservation. We propose to mitigate these problems by a downstream fine-tuning step that corrects for pathological and undesirable extraction results. We implement this idea by using a joint energy-based model which classifies individual glyphs and simultaneously prunes potential out-of-distribution (OOD) samples like rubrications, initials, or ligatures. During model training, we introduce specific margins in the energy spectrum that aid this separation and explore the glyph distribution’s typical set to stabilize the optimization procedure. We observe strong classification at 0.972 AUPRC across 42 lower- and uppercase glyph types on a challenging digital reproduction of Johannes Balbus’ Catholicon, matching the performance of purely discriminative methods. At the same time, we achieve OOD detection rates of 0.989 AUPRC and 0.946 AUPRC for OOD ‘clutter’ and ‘ligatures’ which substantially improves upon recently proposed OOD detection techniques. The proposed approach can be easily integrated into the postprocessing phase of current OCR to aid reproduction and shape analysis research.

This collection is explicitly a book of two halves. In the first (“geographical traditions”) are chapters on the history of geography; in the second (“geographical imaginations”) are chapters that ...

The final chapter considers the Normans as a trans-regional entity and so functions as a counterpart to the broad geographical context of the first chapter. It begins by exploring the debate surrounding Norman administration: whether the Normans were responsible for introducing a particularly advanced governmental administration into areas they occupied, or whether they co-opted pre-existing structures. Here the Domesday Book in England is an important case study. The chapter turns next to the question of Norman identity: whether there was a common sense of ‘Norman-ness’ across the different areas conquered and ruled by Normans, and for how long and to what extent common bonds remained. It considers the extent to which Normans imposed change on the religious institutions and practices (notably the cult of saints) that they encountered locally. Finally, it discusses the Norman cultivation of a sense of being divinely guided in their mission of conquest, and the hotly debated question of whether the Norman conquest of Sicily ought consequently to be considered the ‘real’ First Crusade.