Scholarlink

<p>Handwritten Text Recognition (HTR) remains a challenging task in document digitization, particularly for historical manuscripts written in low-resource languages such as Latin. In this paper, we focus on recognizing Latin texts from 16th–18th century manuscripts, which exhibit a wide range of handwriting styles. To address this, we propose AdapterTrOCR, a modular extension of the TrOCR model that incorporates two adapter modules: one for historical language adaptation and another for handwriting style adaptation. This architecture enables a robust transition from a modern English HTR model to one specialized in historical Latin. Given the limited availability of annotated data, we also explore Handwritten Text Generation (HTG) as a data augmentation strategy. Our results show the effectiveness of modular adaptation and synthetic data in improving HTR performance, achieving reductions in character error rate (CER) by 19.07% to 39.03% and word error rate (WER) by 9.40% to 30.13%. The implementation (code, models and data) is available on <a href="https://rdr.kuleuven.be/dataset.xhtml?persistentId=doi:10.48804/ZPDBKU">KU Leuven RDR</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Handwritten Text Recognition for Historical Latin Manuscripts via Model Adaptation and Synthetic Data Augmentation

  • 期刊论文

  • 发表日期：

    2026年7月26日

查看全文
  • Maria Mihaela Trusca,
  • Mark Depauw,
  • Margherita Fantoli,
  • Violet Soen,
  • Ine de Daele,
  • Kevin Verbruggen,
  • Tim Van de Cruys

摘要

Handwritten Text Recognition (HTR) remains a challenging task in document digitization, particularly for historical manuscripts written in low-resource languages such as Latin. In this paper, we focus on recognizing Latin texts from 16th–18th century manuscripts, which exhibit a wide range of handwriting styles. To address this, we propose AdapterTrOCR, a modular extension of the TrOCR model that incorporates two adapter modules: one for historical language adaptation and another for handwriting style adaptation. This architecture enables a robust transition from a modern English HTR model to one specialized in historical Latin. Given the limited availability of annotated data, we also explore Handwritten Text Generation (HTG) as a data augmentation strategy. Our results show the effectiveness of modular adaptation and synthetic data in improving HTR performance, achieving reductions in character error rate (CER) by 19.07% to 39.03% and word error rate (WER) by 9.40% to 30.13%. The implementation (code, models and data) is available on KU Leuven RDR.