Fingerprint classification using a fuzzy multilayer perceptron

A fuzzy multilayer perceptron is used for the classification of fingerprint patterns. The input vector consists of texturebased features along with some directional features. The output vector is defined in terms of membership values to the three classes, viz.Whorl, Left Loop and Right Loop. Perturbation is produced randomly at pixel locations to generate noisy patterns. This helps to demonstrate the ability of the model in handling distorted fingerprint images. A study is made on the effect of reducing the number of input features while increasing the size of the network on its recognition performance.