Cursive character detection using incremental learning

This paper describes a new hybrid architecture for an artificial neural network classifier that enables incremental learning. The learning algorithm of the proposed architecture detects the occurrence of unknown data and automatically adapts the structure of the network to learn these new data, without degrading previous knowledge. The architecture combines an unsupervised self-organizing map with a supervised perceptron network to form the hybrid self-organizing perceptron (SOP) network. Recognition experiments conducted on isolated characters taken in the context of cursive words show the promising incremental capabilities of this SOP network