Foreground and background information in an HMM-based method for recognition of isolated characters and numeral strings

/in , , /by
Foreground and background information in an HMM-based method for recognition of isolated characters and numeral strings

Britto, Alceu De S. and Sabourin, Robert and Bortolozzi, Flavio and Suen, Ching Y.

Proceedings – International Workshop on Frontiers in Handwriting Recognition, IWFHR 2004

Abstract : In this paper we combine complementary features based on foreground and background information in an HMM-based classifier to recognize handwritten isolated characters and numeral strings. A zoning scheme based on column and row models provides a way of dividing the character into zones without making the features size variant. This strategy allows us to avoid the character normalization, while it provides a way of having information from specific zones of the character. The experimental results on 10 digit classes, 52 character classes and 6 classes of numeral strings of different lengths have shown that the proposed features are highly discrimminant. © 2004 IEEE.

You might also like
Définition et évaluation d’une famille de représentations pour la vérification hors-ligne des signatures
Spectral graph transformer networks for brain surface parcellation
Process for the preparation of lithium aluminum hydride in etheral solvents
Convolutional STN for weakly supervised object localization and beyond
Adaptive ROC-based ensembles of HMMs applied to anomaly detection
Brain fiber clustering using non-negative kernelized matching pursuit
Unsupervised Multi-Target Domain Adaptation through Knowledge Distillation
Laplacian regularized few-shot learning