Language Syntax in a Text Recognition Algorithm

A Markov model for language syntax and its use in a text recognition algorithm is proposed. Syntactic constraints are described by the transition probabilities between classes. The confusion between the feature string for a word and the syntactic classes is also described probabilistically. A modification of the Viterbi algorithm is also proposed that finds a fixed number of sequences of syntactic classes for a given sentence that have the highest probabilities of occurrence, given the feature strings for the words. An experimental application of this approach is demonstrated with a word hypothesization algorithm that produces a number of guesses about the identity of each word in a running text. It is shown that the Viterbi algorithm can significantly reduce the number of words that can possibly match an image.