Multiscale handwriting characterization for writers, classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Multiscale handwriting characterization for writers, classification

Résumé

In this paper, we propose a method for handwritten text characterization based on a multiscale and multiresolution drawing analysis. The approach lies on the definition of four complementary handwritten text visual dimensions: the macro and micro orientation (obtained with a frequencies multiscale image analysis), the text linearity (defined by the merge of connected components), the curvature (measured as a multiresolution high profile deformation) and the complexity (expressed as multiscale drawing distribution entropy). Each feature is studied in an evolution graph that can be expressed as a unique handwritten curve signature. It leads to a description in separable writers families having individual visual characteristics. The results are very promising.
Fichier non déposé

Dates et versions

hal-01552443 , version 1 (02-07-2017)

Identifiants

  • HAL Id : hal-01552443 , version 1

Citer

Véronique Eglin, Stéphane Bres, Carlos Rivero-Moreno. Multiscale handwriting characterization for writers, classification. DAS: Document Analysis System VI, Jan 2004, Florence, Italy, Italy. pp.337-341. ⟨hal-01552443⟩
65 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More