PT Journal
AU Jose Antonio Rodriguez
   Florent Perronnin
   Gemma Sanchez
   Josep Llados
TI Unsupervised writer adaptation of whole-word HMMs with application to word-spotting
SO Pattern Recognition Letters
JI PRL
PY 2010
BP 742–749
VL 31
IS 8
DI 10.1016/j.patrec.2010.01.007
DE Word-spotting; Handwriting recognition; Writer adaptation; Hidden Markov model; Document analysis
AB 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.
ER