摘要：Biometrics of the ear is a recent tool for the recognition of people with the great advantage that ears seem to maintain their structure with age. This paper describes the application of modular neural network architecture, with pre-processing, to improve the recognition of people using images of the Ear as a biometric measure. The Ear database used in this work was obtained from the University of Science and Technology of Beijing (USTB). We show the results obtained with the modular neural network, the optimization using genetic algorithms, and the integration using different methods: Winner Takes All (WTA), type-1 fuzzy integration and fuzzy integration optimized by genetic algorithms. The behavior of the simulations show a good identification, using the appropriate pre-processing, integrators and the best structure found by the genetic algorithm.
