A self-organizing network with fuzzy hyperellipsoidal classifying and its application in handwritten numeral recognition

Abstract

This paper proposes a self-organizing network with the fuzzy hyperellipsoid-classifier (FHECFN) and utilizes it to recognize handwritten numerals. Based on the clustering result of SOM, FHECFN divides the center that performs worse taking the advantage of the fuzzy hyperellipsoidal clustering algorithm. When reaching the satisfying requirement, the network stops divining and then obtains the suitable number of prototypes and the hyperellipsoidal classifying result. With the supervised learning algorithm, such as learning vector quantization, the network achieves a better learning result and in the experiments of recognizing the handwritten numerals, the network shows a promising performance.