This paper describes a hidden Markov model-based approach designed to recog
nize off-line unconstrained handwritten words for large vocabularies. After
preprocessing, a word image is segmented into letters or pseudoletters and
represented by two feature sequences of equal length, each consisting of a
n alternating sequence of shape-symbols and segmentation-symbols, which are
both explicitly modeled. The word model is made up of the concatenation of
appropriate letter models consisting of elementary HMMs and an HMM-based i
nterpolation technique is used to optimally combine the two feature sets. T
wo rejection mechanisms are considered depending on whether or not the word
image is guaranteed to belong to the lexicon. Experiments carried out on r
eal-life data show that the proposed approach can be successfully used for
handwritten word recognition.