RPalk/czech_vital_records

捷克历史重要记录数据集是一个包含19世纪捷克出生、婚姻和死亡登记的手动注释图像的集合。该数据集专门用于支持自动化历史文档处理的研究，包括布局分析、手写文本识别和专门档案文档的后处理方法。数据集包含原始文档扫描和PageXML转录，文档来源于布拉格国家区域档案馆的数字化收藏。该数据集是在硕士论文《使用手写文本识别自动转录和搜索历史记录》的框架下收集的。

The Czech Historical Vital Records Dataset is a collection of manually annotated images of 19th-century Czech birth, marriage, and death registers. This dataset was specifically created to support research into automated historical document processing, including layout analysis, handwritten text recognition, and post-processing methods for specialized archival documents. The dataset contains original documents scans along with PageXML transcriptions. The documents for the dataset were sourced from the digital collections of the State Regional Archives in Prague. The dataset was collected as part of the Masters Thesis: Automated Transcription and Search in Historical Records Using Handwritten Text Recognition.