Abstract
Handwritten text recognition for historical documents remains challenging due to handwriting variability, degraded sources, and limited layout-aware annotations. In this work, we address annotation errors - particularly hyphenation issues - in the Bullinger correspondence, a large 16th-century letter collection. We introduce a self-training method based on a CTC alignment algorithm that matches full transcriptions to text line images using dynamic programming and model output probabilities trained with the CTC loss. Our approach improves performance (e.g., by 1.1 percentage points CER with PyLaia) and increases alignment accuracy. Interestingly, we find that weaker models yield more accurate alignments, enabling an iterative training strategy. We release a new manually corrected subset of 100 pages from the Bullinger dataset, along with our code and benchmarks. Our approach can be applied iteratively to further improve the CER as well as the alignment quality for text recognition pipelines. Code and data are available via this https URL.
Abstract (translated)
历史文献的手写文本识别由于书写变化性、退化来源和有限的版面感知标注而仍然具有挑战性。在本研究中，我们解决了布林格通信中的注释错误问题，特别是连字符问题，这是16世纪的一大批信件集合。我们提出了一种基于CTC对齐算法的自训练方法，该方法利用动态规划和使用CTC损失训练得到的概率模型输出，将全文转录与文本行图像进行匹配。我们的方法提高了性能（例如，在PyLaia中字符错误率降低了1.1个百分点），并增加了对齐准确性。有趣的是，我们发现较弱的模型产生了更准确的对齐结果，这使迭代训练策略成为可能。 我们发布了从布林格数据集中手动修正的一个包含100页的新子集，并提供了我们的代码和基准测试结果。我们的方法可以被反复应用于进一步提高字符错误率（CER）以及文本识别管道中的对准质量。代码和数据可通过此链接获取：[请在此插入链接]。 原文献中的网址无法直接显示，您可以在相应的研究发布平台上查找该论文的官方链接以访问相关资源。
URL
https://arxiv.org/abs/2508.07904
