Integration of contextual information in handwriting recognition systems

/in , , /by
Integration of contextual information in handwriting recognition systems

Grandidier, F. and Sabourin, R. and Suen, C. Y.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 2003

Abstract : This paper investigates different strategies allowing integration of contextual information during the feature extraction stage of a cursive handwriting HMM-based recognition system. First we propose to use linear discriminant analysis (LDA) in order to integrate the class information during feature set building. Secondly several zoning strategies are used to integrate local contextual information. Finally, a weighting technique is proposed in association with zoning with the aim of integrating handwriting style. Some experiments were carried out and the results show the interest of the proposed strategies.

You might also like
A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome
Adversarial learning of general transformations for data augmentation
Attention-based dynamic subspace learners for medical image analysis
Évaluation d’un classificateur de type LVQ de Kohonen pour la vérification automatique de l’identité
Estimating accurate multi-class probabilities with support vector machines
Deep learning in object detection
A survey of techniques for incremental learning of HMM parameters
On the evaluation of the carbon dioxide solubility in polymers using gene expression programming