Kinematic Reconstruction of Calligraphic Traces from Shape Features

Berio, Daniel; Leymarie, Frederic Fol and Plamondon, Rejean. 2018. Kinematic Reconstruction of Calligraphic Traces from Shape Features. Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence, 1(1), pp. 762-767. [Article]

Text (© ACM, 2018. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. See citation for link to the definitive version.)
lognormality_2017.pdf - Published Version

Download (4MB) | Preview
Official URL:

Abstract or Description

Our goal is to be able to reproduce computationally calligraphic traces, e.g. as found in the art practices of graffiti and various forms of more traditional calligraphy, while mimicking the production process of such art forms. We design our user interfaces in a procedural generation and computer aided design (CAD) setting. As a result, we seek to seamlessly work between data used in design packages (without kinematics) and data easily digitised by users (e.g. online, with kinematics). To achieve these goals, we propose a method that allows to reconstruct kinematics from solely the geometric trace of handwritten trace in the form of parameters of the Sigma-Lognormal model. We purposely ignore the kinematics possibly embedded in the data in order to treat online data and vector patterns with the same procedure.

Item Type:



sigma-lognormal, curve reconstruction, medial axis, graffiti, handwriting

Departments, Centres and Research Units:



1 January 2018Accepted
1 May 2018Published

Item ID:


Date Deposited:

07 Jun 2018 08:38

Last Modified:

17 Jun 2021 09:54

Peer Reviewed:

Yes, this version has been peer-reviewed.


View statistics for this item...

Edit Record Edit Record (login required)