Title | ||
---|---|---|
Comparing Machine Learning Approaches for Table Recognition in Historical Register Books |
Abstract | ||
---|---|---|
We present in this paper experiments on Table Recognition in hand-written register books. We first explain how the problem of row and column detection is modelled, 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 Archives of the Diocese of Passau. With an F-1 score of 89, both methods provide a quality which allows for Information Extraction. Software and dataset are open source/data. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/DAS.2018.44 | 2018 13th IAPR International Workshop on Document Analysis Systems (DAS) |
Keywords | Field | DocType |
Machine Learning,Document Analysis and Understanding,Table Recognition | Conditional random field,Graph,F1 score,Computer science,Information extraction,Software,Artificial intelligence,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-5386-3347-2 | 4 | 0.48 |
References | Authors | |
8 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stéphane Clinchant | 1 | 244 | 19.82 |
Hervé Déjean | 2 | 377 | 48.52 |
Jean-Luc Meunier | 3 | 243 | 39.36 |
Eva Maria Lang | 4 | 4 | 1.16 |
Florian Kleber | 5 | 57 | 8.15 |