发表机构
Friedrich-Alexander-Universität Erlangen-Nürnberg; Johannes Gutenberg-Universität Mainz; Staatsbibliothek zu Berlin; Universität Heidelberg（弗里德里希-亚历山大大学埃尔朗根-纽伦堡; 约翰内斯·古腾堡大学美因茨; 柏林国家图书馆; 海德堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文研究层级结构能否辅助泰罗尼安音符自动识别，对比扁平与层级模型，发现层级模型在未适应时表现更优，但少样本适应后扁平模型最佳。
AI 中文摘要
泰罗尼安音符通常被认为是第一种拉丁速记系统，以其庞大而精细的符号库存而著称。它们的高度视觉相似性和庞大的类别集使得人工阅读耗时费力，使得包含泰罗尼安音符的手稿对许多研究者来说难以利用。自动识别也颇具挑战性，因为模型必须区分笔画形状和符号结构上的细微差异，而现实训练数据仍然稀缺。然而，标准的扁平分类器并未明确利用相关符号之间的视觉或结构关系。本文研究泰罗尼安音符之间的结构关系是否能支持自动识别。我们使用马丁·赫尔曼的《泰罗尼安音符超级文本》（Supertextus Notarum Tironianarum, SNT），它提供了理想化的符号形式和泰罗尼安音符的层级组织。我们比较了扁平ResNet18、ConvNeXt、移位窗口变换器（Swin）和视觉变换器（ViT）分类器与层级深度卷积神经网络（HD-CNN）风格的粗到细模型以及基于视觉类别清理和基于相似性重新聚类的层级感知路由模型。这些模型在手写样本和来自《维吉尔·图罗嫩西斯》（Vergilius Turonensis）的手稿域样本上进行评估，包括有和没有对手稿域进行有限少样本适应的情况。结果表明，扁平模型和层级模型的相对性能取决于适应情况。在《维吉尔·图罗嫩西斯》上，HD-CNN在未适应的情况下取得了最佳Top-1结果，准确率为45.43%，而扁平分类在少样本适应后取得了最佳Top-1结果，准确率为82.09%。总体而言，结果表明层级结构可以支持泰罗尼安音符识别，尤其是在未适应条件下。
英文摘要
Tironian notes are generally regarded as the first Latin shorthand system and are notable for their large, fine-grained symbol inventory. Their high visual similarity and large class set make manual reading time-consuming, leaving manuscripts that contain Tironian notes inaccessible to many researchers. Automatic recognition is also challenging because models must distinguish subtle differences in stroke shape and sign structure while realistic training data remain scarce. However, standard flat classifiers do not explicitly use visual or structural relations between related signs. This paper investigates whether structural relationships between Tironian notes can support automatic recognition. We use the Supertextus Notarum Tironianarum (SNT) by Martin Hellmann, which provides idealized sign forms and a hierarchical organization of Tironian notes. We compare flat ResNet18, ConvNeXt, Shifted Window Transformer (Swin), and Vision Transformer (ViT) classifiers with Hierarchical Deep Convolutional Neural Network (HD-CNN)-style coarse-to-fine models and hierarchy-aware routing models based on visual class cleaning and similarity-based re-clustering. The models are evaluated on handwritten samples and manuscript-domain samples from Vergilius Turonensis, both with and without limited few-shot adaptation to the manuscript domain. The results show that the relative performance of flat and hierarchical models depends on adaptation. On Vergilius Turonensis, HD-CNN achieves the best non-adapted Top-1 result with 45.43%, while flat classification reaches the best Top-1 result after few-shot adaptation with 82.09%. Overall, the results indicate that hierarchical structure can support Tironian note recognition, especially under non-adapted conditions.
CommentsAccepted at the 2026 ICDAR Workshop on Computational Paleography (IWCP). 25 pages, including supplementary material
