将历史文献文字行识别与版面分析结合，实现拉丁文古籍完整页面的精准转写。
FP-THD: Full page transcription of historical documents
- 用版面分析提取文字行，再交由OCR模型生成完整页面文本。
- 在多数据集上验证，对手写、印刷体及多语言文本均表现良好。
- 适合历史文献数字化、古籍研究者使用，尤其关注字符特性的场景。
15至16世纪拉丁文历史文献的转写面临特殊挑战，需保留具有特定含义的字符与符号以维持原文风格与意义。本文提出一种转写管道，将现有文字行识别方法与版面分析模型结合。通过版面分析模型解析历史文本图像并提取文字行，再交由OCR模型生成完整页面的数字化结果。实验表明，该流程能高效处理整页内容。在多个数据集上的评估显示，掩码自编码器可有效应对不同类型的文本，包括手写体、印刷体及多语言文本。
原文摘要 · Abstract (English)
The transcription of historical documents written in Latin in XV and XVI centuries has special challenges as it must maintain the characters and special symbols that have distinct meanings to ensure that historical texts retain their original style and significance. This work proposes a pipeline for the transcription of historical documents preserving these special features. We propose to extend an existing text line recognition method with a layout analysis model. We analyze historical text images using a layout analysis model to extract text lines, which are then processed by an OCR model to generate a fully digitized page. We showed that our pipeline facilitates the processing of the page and produces an efficient result. We evaluated our approach on multiple datasets and demonstrate that the masked autoencoder effectively processes different types of text, including handwritten, printed and multi-language.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。