Efficient Annotation of Medieval Charters

TL;DR

This paper introduces an efficient object detection-based method for annotating medieval charters, significantly reducing expert time and improving annotation quality, with additional techniques for physical length estimation using neural networks.

Contribution

It presents a novel annotation approach for medieval charters that outperforms pixel-level segmentation and incorporates regression neural networks for physical length estimation.

Findings

Object detection approach is more efficient than pixel segmentation.

Annotation quality can match or surpass pixel-level methods.

Neural networks effectively predict physical length from image patches.

Abstract

Diplomatics, the analysis of medieval charters, is a major field of research in which paleography is applied. Annotating data, if performed by laymen, needs validation and correction by experts. In this paper, we propose an effective and efficient annotation approach for charter segmentation, essentially reducing it to object detection. This approach allows for a much more efficient use of the paleographer's time and produces results that can compete and even outperform pixel-level segmentation in some use cases. Further experiments shed light on how to design a class ontology in order to make the best use of annotators' time and effort. Exploiting the presence of calibration cards in the image, we further annotate the data with the physical length in pixels and train regression neural networks to predict it from image patches.