Combination of deep learning and syntactical approaches for the interpretation of interactions between text-lines and tabular structures in handwritten documents

Camille Guerry Bertrand Coüasnon 1 Aurélie Lemaitre 1
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : In this article, we present our work on baseline detection in images of historical documents. This work focuses on handwritten documents containing tabular structures. One of the difficulties of this kind of documents is the strong interaction between text and tabular structures. This interaction leads to ambiguous cases for which recognition systems often over-or sub-segment baselines. The interest of our method is to combine contextual and structural knowledge in order to interpret properly this interaction. Our combination is able to merge heterogeneous information obtained with a deep-learning approach (for contextual elements) and a syntactical approach (for structural elements). Our grammatical description consists on a logical description of the intersections between text-lines and vertical rulings of detected tables. Intersections are described thanks to physical indicators extracted from images: vertical rulings, hypothetical text-lines, begin-and end-indicators of text-lines. We show on cBAD competition [4] (competition on baseline detection) that the combination of heterogeneous knowledge (structural and contextual information) improves baseline detection in handwritten documents. We obtain better scores than the best method published until now on this competition.
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02303293
Contributor : Camille Guerry <>
Submitted on : Wednesday, October 2, 2019 - 10:58:09 AM
Last modification on : Friday, October 4, 2019 - 1:56:13 AM

File

Combination of deep learning a...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02303293, version 1

Citation

Camille Guerry, Bertrand Coüasnon, Aurélie Lemaitre. Combination of deep learning and syntactical approaches for the interpretation of interactions between text-lines and tabular structures in handwritten documents. 15th International Conference on Document Analysis and Recognition (ICDAR), Sep 2019, Sydney, Australia. ⟨hal-02303293⟩

Share

Metrics

Record views

13

Files downloads

12