Éditeur(s) : HAL CCSD
Résumé : International audience
The large majority of methods proposed in literature for handwriting recognition assume that words are produced drawing large parts of the ink without lifting the pen, other than horizontal bars and dots. This fundamental assumption, however, does not always hold: while some educational systems provide explicit training for producing continuous handwriting, minimizing the number of pen-up during the production of a word, others do not. As a consequence, whenever the handwriting presents pen-up within a word, the recognition performance can drop significantly. In a preliminary study, we presented an algorithm for discriminating among different types of ink appearing in handwriting, namely isolated characters, cursive, dots, horizontal and vertical bars, based on the use of a suitable set of features. In this paper, we have characterized the discriminative power of each considered feature according to different measures and we have proposed a method for combining the different feature rankings. We have also used the Fischer's Linear Discriminant Analysis (LDA) for exhaustively selecting the best feature subsets with increasing number of features. Finally, we have compared the results obtained by using the feature subsets provided by LDA with those obtained with the feature subsets selected according to our feature ranking. The experimental results, on different datasets of handwritten words, showed that our approach successfully achieves its aim allowing to reduce the computational cost without affecting the overall performance of the recognition process.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165877
https://hal.univ-antilles.fr/hal-01165877
https://hal.univ-antilles.fr/hal-01165877/document
https://hal.univ-antilles.fr/hal-01165877/file/IGS_2015_submission_13.pdf

Éditeur(s) : HAL CCSD Elsevier Masson
Résumé : International audience
The two experiments reported in the present paper concern (i) the differential imagery value of French and Creole and (ii) the influence of language on the recall of sequences of patterned movements in a bilingual population. Creole words were obtained a higher imagery value than French words, certainly because Creole is an oral and vernacular language. Motor recall scores were better when the sequence was presented in Creole compared to French. The generation of visual images by Creole would facilitate the memorization and recall of new sequences of movements. The effect of language on imagery value of words and motor recall among bilingual French–Creole subjects was discussed in terms of nature of information encoding in each language.
Les deux expérimentations relatées dans cet article évaluent la valeur d'imagerie de mots et le rappel moteur d'enchaînements auprès de bilingues français–créole en faisant varier la langue de présentation. Les mots en créole, supposés susciter plus facilement des images mentales visuelles, car le créole est une langue orale et vernaculaire, ont effectivement obtenu une cote plus élevée que les mots français sur l'échelle de valeur d'imagerie. L'évocation d'images visuelles facilitant la mémo-risation et la planification de séquences de mouvements, les performances de rappel obtenues à partir des consignes en créole ont été supérieures à celles obtenues en français. Les effets de la langue de présentation sur la valeur d'imagerie des mots et le rappel moteur d'enchaînements de morphocinè-ses auprès des participants bilingues sont discutés en termes de nature d'encodage de l'information verbale dans chacune des langues.
ISSN: 0033-2984

hal-01540163
https://hal.univ-antilles.fr/hal-01540163
DOI : 10.1016/j.psfr.2005.05.011