Hierarchical decomposition of handwritten
manuscripts layouts

Vincent Malleron (1, 2) , Véronique Eglin (1) , Hubert Emptoz (1) , Stéphanie Dord-Crouslé (2) , Philippe Régnier (2)

1 imagine - Extraction de Caractéristiques et Identification
2 LIRE - Littérature, idéologies, représentations, XVIIIe-XIXe siècles

In this paper we propose a new approach to improve electronic editions of literary corpus, providing an efficient estimation of manuscripts pages structure. In any handwriting documents analysis process, structure recognition is an important issue. The presence of variable inter-line spaces, of inconstant base-line skews, overlappings and occlusions in unconstrained ancient 19th handwritten documents complicates the structure recognition task. Text line and fragment extraction is based
on the connexity labelling of the adjacency graph at different resolution
levels, for borders, lines and fragments extraction.

Mots clés: text lines and fragments extraction; graph; handwriting

Mots clés: extraction de lignes de texte; extraction de fragments; graphes; écriture manuscrite

Domaines: Littératures; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Vincent Malleron, Véronique Eglin, Hubert Emptoz, Stéphanie Dord-Crouslé, Philippe Régnier. Hierarchical decomposition of handwritten
manuscripts layouts. Computer Analysis of Images and Patterns, Sep 2009, Muenster, Germany. pp.221-228, ⟨10.1007/978-3-642-03767-2⟩. ⟨halshs-00420059⟩