Recognition of Unconstrained Handwritten Words Using Markov Random Fields and HMMs
Résumé
In this paper we present a system for recognition of handwritten words on literal check amounts which advantageously combines HMMs and Markov random fields (MRFs). It operates, in a holistic manner, at pixel level on height normalised word images which are viewed as random field realizations. The HMM analyses the image along the horizontal writing direction, in a specific state observation probability being given by the column product of causal MRF like pixel conditional probabilities.Aspects concerning definition, training and recognition via this type of model and experiments performed are developed throughout the paper.