A Progressive Learning Method for Symbol Recognition

This paper deals with a progressive learning method for symbol recognitionwhich improves its own recognition rate when new symbols are recognized in graphicdocuments. We propose a discriminant analysis method which provides allocation rulesfrom a training set of labelled data. However a discriminant analysis method is efficientonly if the training set and the test data are defined in the same conditions but it israre in real life. In order to overcome this problem, a conditional vector is added toeach instance to take into account the parasitic effects between the test data and thetraining set. We also propose an adaptation to consider the user feedback