An Online Hand-Drawn Electric Circuit Diagram Recognition System Using Hidden Markov Models - Laboratoire de Mathematiques Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

An Online Hand-Drawn Electric Circuit Diagram Recognition System Using Hidden Markov Models

Résumé

In this paper we experiment the capabilities of Hidden Markov Models (HMM) to model the time-variant signal produced by the movement of a pen when drawing a sketch such as an electrical circuit diagram. We consider that the sketches have been generated by a two-level stochastic process. The underlying process governs the stroke production from a neuro-motor control point of view: go straight, change direction, produce a curve. A second stochastic process delivers the observed signal, which is a sequence of sampled points. Three different architectures of HMM are proposed and compared. On a dataset of 100 hand-drawn sketches, the proposed method allows to classify correctly more than 83% of the points with respect to the connector and symbol classes.
Fichier non déposé

Dates et versions

hal-00440790 , version 1 (11-12-2009)

Identifiants

Citer

Yingmin Zhang, Christian Viard-Gaudin, Liming Wu. An Online Hand-Drawn Electric Circuit Diagram Recognition System Using Hidden Markov Models. International Symposium on Computer Science and Computational Technology, Dec 2008, Shanghaï, China. pp.143-148, ⟨10.1109/ISISE.2008.222⟩. ⟨hal-00440790⟩
159 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More