Strategies for handwritten words recognition using hidden Markov models

Several approaches for the application of hidden Markov models to the recognition of handwritten words are described. All approaches share the same description of words through strings of symbols. They differ with respect to the size of the vocabulary which has to be recognized. The authors distinguish between two cases: where the vocabulary is small and constant, and where the vocabulary is limited but dynamic in the sense that it is a varying subset of an open one. The authors also describe an application of hidden Markov models to the representation of contextual knowledge and propose some strategies to reject unreliable word interpretations, in particular when the word corresponding to the image is not guaranteed to belong to the lexicon.<<ETX>>