Fingerprint Authentication using Adaptive RBF

In this paper, we have proposed an adaptive radial basis function neural network which is based on adaptions of center and spread parameters involved in network design. This adaption is achieved through stochastic approach. Proposed adaptive form of architecture is applied to authenticate the fingerprint images. From individual fingerprint image, features based change is given to define the corresponding values of weights and radial basis function. Proposed method has shown remarkable advantage over fixed radial basis function neural network in feature extraction from fingerprint images