When dealing with a pattern recognition task two major issues must be faced
: firstly, a feature extraction technique has to be applied to extract usef
ul representations of the objects to be recognized; secondly, a classificat
ion algorithm must be devised in order to produce a class hypothesis once a
pattern representation is given. Adaptive graphical pattern recognition is
proposed as a new approach to face these two issues when neither a purely
symbolic nor a purely sub-symbolic representation seems adequate for the pa
tterns. This approach is based on appropriate structured representations of
patterns which are, subsequently, processed by recursive neural networks,
that can be trained to perform the given classification task using connecti
onist-based learning algorithms. In the proposed framework, the joint role
of the structured representation and learning makes it possible to face tas
ks in which input patterns are affected by many different sources of noise.
We report some results that show how the proposed scheme can produce a ver
y promising performance for the classification of company logos corrupted b
y noise. (C) 2001 Pattern Recognition Society. Published by Elsevier Scienc
e Ltd. All rights reserved.