Unsupervised writer adaptation of whole-word HMMs with application to word-spotting

José A. Rodríguez-Serrano, Florent Perronnin, Gemma Sánchez, Josep Lladós

Producció científica: Article en revista indexadaArticleAvaluat per experts

13 Cites (Scopus)


In this paper we propose a novel approach for writer adaptation in a handwritten word-spotting task. The method exploits the fact that the semi-continuous hidden Markov model separates the word model parameters into (i) a codebook of shapes and (ii) a set of word-specific parameters. Our main contribution is to employ this property to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best of our knowledge, this is the first work dealing with adaptation for word-spotting. The preliminary version of this paper obtained an IBM Best Student Paper Award at the 19th International Conference on Pattern Recognition.

Idioma originalAnglès
Pàgines (de-a)742-749
Nombre de pàgines8
RevistaPattern Recognition Letters
Estat de la publicacióPublicada - 1 de juny 2010
Publicat externament


Navegar pels temes de recerca de 'Unsupervised writer adaptation of whole-word HMMs with application to word-spotting'. Junts formen un fingerprint únic.

Com citar-ho