Enlightened by the idea of metasynthesis, two integration approaches f
or handwritten Chinese character recognition are proposed in this pape
r. The first one is Integration based on a Linear Model and the second
one is Network Integration based on Supervised Learning. Compared wit
h previous integration approaches, the proposed methods succeed in aut
omatically acquiring the parameters of the integrated systems by super
vised learning which is very important for the large number of classes
of pattern recognition problems. The experimental results show that t
he performances of the synthesized systems are much better than any of
the individual classifiers. (C) 1997 Pattern Recognition Society. Pub
lished by Elsevier Science Ltd.