@Article{JoseAntonioRodriguez2009,
author="Jose Antonio Rodriguez
and Florent Perronnin",
title="Handwritten word-spotting using hidden Markov models and universal vocabularies",
journal="Pattern Recognition",
year="2009",
publisher="Elsevier",
volume="42",
number="9",
pages="2103--2116",
optkeywords="Word-spotting",
optkeywords="Hidden Markov model",
optkeywords="Score normalization",
optkeywords="Universal vocabulary",
optkeywords="Handwriting recognition",
abstract="Handwritten word-spotting is traditionally viewed as an image matching task between one or multiple query word-images and a set of candidate word-images in a database. This is a typical instance of the query-by-example paradigm. In this article, we introduce a statistical framework for the word-spotting problem which employs hidden Markov models (HMMs) to model keywords and a Gaussian mixture model (GMM) for score normalization. We explore the use of two types of HMMs for the word modeling part: continuous HMMs (C-HMMs) and semi-continuous HMMs (SC-HMMs), i.e. HMMs with a shared set of Gaussians. We show on a challenging multi-writer corpus that the proposed statistical framework is always superior to a traditional matching system which uses dynamic time warping (DTW) for word-image distance computation. A very important finding is that the SC-HMM is superior when labeled training data is scarce---as low as one sample per keyword---thanks to the prior information which can be incorporated in the shared set of Gaussians.",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=1053), last updated on Thu, 19 Dec 2013 12:26:24 +0100",
issn="0031-3203",
doi="10.1016/j.patcog.2009.02.005"
}