Handwritten recognition with multiple classifiers for restricted lexicon
J.J. de Oliveira, Marcelo N. Kapp, Cinthia Obladen de Almendra Freitas, J.M. de Carvalho, Robert Sabourin · 2004
This paper presents a multiple classifier system applied to the handwritten word recognition (HWR) problem. The goal is to analyse the influence of different global classifiers taken in isolation as well as combined in a particular HWR task. The application proposed is the recognition of the Portuguese handwritten names of the months. The strategy takes advantage of the complementary mechanisms of three different classifiers: conventional neural network, class-modular neural network and hidden Markov models, yielding a multiple classifier that is more efficient than either individual technique. The recognition rates obtained vary from 75.9% using the standalone HMM classifier to 96.0% considering the classifier combination.