Synthetic parameters for handwriting classification

/in , , /by
Synthetic parameters for handwriting classification

Bouletreau, V. and Vincent, N. and Sabourin, R. and Emptoz, H.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 1997

Abstract : In this paper, we present a new family of parameters for handwriting analysis based on the fractal behavior of writing. These parameter allow the classification of writing into different families which could be used as a preliminary step for recognition methods. They also constitute a way to quantify some legibility properties and we show that they can be useful for cognitive approaches of handwriting analysis.

You might also like
CAT: Constrained adversarial training for anatomically-plausible semi-supervised segmentation
Domain-specific face synthesis for video face recognition from a single sample per person
Using deep convolutional neural networks for neonatal brain image segmentation
Local discriminative characterization of MRI for Alzheimer’s disease
Multiregion level-set partitioning of synthetic aperture radar images
Mise au point d’un utilitaire graphique interactif pour la définition et la validation des relations spatiales entre primitives géométriques
Curriculum semi-supervised segmentation
Writer-independent feature learning for Offline Signature Verification using Deep Convolutional Neural Networks