ICDAR 2011 Book Structure Extraction Competition

Antoine Doucet (1) , Gabriella Kazai (2) , Jean-Luc Meunier (3)

1 Equipe Hultech - Laboratoire GREYC - UMR6072
2 Microsoft Research [Redmond]
3 Xerox Research Centre Europe [Meylan]

In this paper, we summarize the 2nd Book Structure Extraction competition run at ICDAR 2011. Its goal is to evaluate and compare automatic techniques for deriving structure information from digitized books, which could then be used to aid navigation inside the books. More specifically, the task that participants are faced with is to construct hyperlinked tables of contents for a collection of 1,000 digitized books. This paper reviews the setup of the competition, the book collection used in the task, and the measures used for the evaluation. It further presents the outcome of the competition: an additional ground truth of 513 book tables of contents, contributed by 6 institutions, and the result performance of the 4 participating research teams.

Mots clés: component; formatting; style; styling

Domaines: Traitement du texte et du document

Antoine Doucet, Gabriella Kazai, Jean-Luc Meunier. ICDAR 2011 Book Structure Extraction Competition. Eleventh International Conference on Document Analysis and Recognition (ICDAR'2011), Sep 2011, Pekin, China. pp.1501--1505, ⟨10.1109/ICDAR.2011.298⟩. ⟨hal-01069019⟩