# Comparing Machine Learning Approaches for Table Recognition in Historical Register Books

arXiv: https://arxiv.org/abs/1906.11901 · HTML: https://mlsanity.com/paper/1906.11901/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling](https://mlsanity.com/paper/2303.06949/) (2023)
- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [Applications of Machine Learning in Document Digitisation](https://mlsanity.com/paper/2102.03239/) (2021)
- [LayoutXLM vs. GNN: An Empirical Evaluation of Relation Extraction for Documents](https://mlsanity.com/paper/2206.10304/) (2022)
- [InstructTable: Improving Table Structure Recognition Through Instructions](https://mlsanity.com/paper/2604.02880/) (2026)
- [Creating a Historical Migration Dataset from Finnish Church Records, 1800-1920](https://mlsanity.com/paper/2506.07960/) (2025)

## Abstract (arXiv)

We present in this paper experiments on Table Recognition in hand-written registry books. We first explain how the problem of row and column detection is modeled, and then compare two Machine Learning approaches (Conditional Random Field and Graph Convolutional Network) for detecting these table elements. Evaluation was conducted on death records provided by the Archive of the Diocese of Passau. Both methods show similar results, a 89 F1 score, a quality which allows for Information Extraction. Software and dataset are open source/data.