A new fuzzy geometric representation for online isolated character recognition

Abstract

Introduces a fuzzy representation for isolated character description. This representation maps a character from its original sequence of 2D coordinates into a fuzzy vector space that can thereafter serve as input to any artificial neural network classifier. Recognition experiments on isolated digits extracted from the UNIPEN database are their conducted to evaluate the performances of the proposed representation using a hybrid Kohonen-perceptron (KP) neural network.