The work in this paper describes the training and evaluation of machine learning (ML) techniques for the classification of cuneiform signs. There is a lot of variability in cuneiform signs, depending on where they come from, for what and by whom they were written, but also how they were digitized. This variability makes it unlikely that an ML model trained on one dataset will perform successfully on another dataset. This contribution studies how such differences impact that performance. Based on our results and insights, we aim to influence future data acquisition standards and provide a solid foundation for future cuneiform sign classification tasks. The ML model has been trained and tested on handwritten Old Babylonian (c. 2000-1600 B.C.E.) documentary texts inscribed on clay tablets originating from three Mesopotamian cities (Nippur, Dūr-Abiešuh and Sippar). The presented and analysed model is ResNet50, which achieves a top-1 score of 87.1% and a top-5 score of 96.5% for signs with at least 20 instances. As these automatic classification results are the first on Old Babylonian texts, there are currently no comparable results.

The cuneiform writing system served as the medium for transmitting knowledge in the ancient Near East for a period of over three thousand years. Cuneiform signs have a complex internal structure which is the subject of expert paleographic analysis, as variations in sign shapes bear witness to historical developments and transmission of writing and culture over time. However, prior automated techniques mostly treat sign types as categorical and do not explicitly model their highly varied internal configurations. In this work, we present an unsupervised approach for recovering the fine-grained internal configuration of cuneiform signs by leveraging powerful generative models and the appearance and structure of prototype font images as priors. Our approach, ProtoSnap, enforces structural consistency on matches found with deep image features to estimate the diverse configurations of cuneiform characters, snapping a skeleton-based template to photographed cuneiform signs. We provide a new benchmark of expert annotations and evaluate our method on this task. Our evaluation shows that our approach succeeds in aligning prototype skeletons to a wide variety of cuneiform signs. Moreover, we show that conditioning on structures produced by our method allows for generating synthetic data with correct structural configurations, significantly boosting the performance of cuneiform sign recognition beyond existing techniques, in particular over rare signs. Cuneiform signs have complex internal structures which varied significantly across the eras, cultures, and geographic regions among which cuneiform writing was used. The study of these variations is part of a field called paleography, which is crucial for understanding the historical context of attested writing (Biggs, 1973; Homburg, 2021). However, while computational methods show promise for aiding experts in analyzing cuneiform texts (Bogacz and Mara, 2022), they are challenged by the vast variety of complex sign variants and their visual nature: Represented as wedge-shaped imprints in clay tablets which have often sustained physical damage, cuneiform appears as shadows on a non-uniform clay surface which may even be difficult for human experts to identify under non-optimal lighting conditions (Taylor, 2015).

One of the most significant problems in cuneiform pedagogy is the process of looking up unknown signs, which often involves a tedious page-by-page search through a sign list. This paper proposes a new "recursive encoding" for signs, which represents the arrangement of strokes in a way a computer can process. A series of new algorithms then offers students a new way to look up signs by any distinctive component, as well as providing new ways to render signs and tablets electronically.

Broken and scorched black by fire, the dense, wedge-shaped marks etched into the ancient clay tablets are only just visible under the soft light at the British Museum. These tiny signs are the remains of the world's oldest writing system: cuneiform. Developed more than 5,000 years ago in Mesopotamia, the land between the Tigris and Euphrates rivers where modern-day Iraq now lies, cuneiform captured life in a complex and fascinating civilisation for some three millennia. From furious letters between warring royal siblings to rituals for soothing a fractious baby, the tablets offer a unique insight into a society at the dawn of history. An estimated half a million of them have been excavated, and more are still buried in the ground.