Handwritten signatures recognizer by its envelope and strokes layout using HMM's

Título:	Handwritten signatures recognizer by its envelope and strokes layout using HMM's
Autores/as:	Sánchez, J. A. Travieso, C. M. Alonso, I. G. Ferrer, M. A.
Clasificación UNESCO:	3307 Tecnología electrónica
Palabras clave:	Handwriting recognition Hidden Markov models Automatic speech recognition Karhunen-Loeve transforms Fast Fourier transforms
Fecha de publicación:	2001
Publicación seriada:	IEEE Annual International Carnahan Conference on Security Technology, Proceedings
Conferencia:	35th Annual International Carnahan Conference on Security Technology 35th Annual 2001 International Carnahan Conference on Security Technology
Resumen:	A method for the automatic recognition of offline handwritten signatures using both global and local features is described. As global features, we use the envelope of the signature sequenced as polar coordinates; and as local features we use points located inside the envelope that describe the density or distribution of signature strokes. Each feature is processed as a sequence by a hidden Markov Model (HMM) classifier. The results of both classifiers are linearly combined, obtaining a recognition ratio of 95.15% with a database of 60 handwritten signatures.
URI:	http://hdl.handle.net/10553/46173
ISBN:	0-7803-6636-0
Fuente:	IEEE Annual International Carnahan Conference on Security Technology, Proceedings, p. 267-271
Colección:	Actas de congresos

Vista completa