Date Added: Sep 2010
In this paper, the authors propose an approach for the classification of fingerprint databases. It is based on the fact that a fingerprint image is composed of regular texture regions that can be successfully represented by co-occurrence matrices. So, they first extract the features based on certain characteristics of the co-occurrence matrix and then they use these features to train a neural network for classifying fingerprints into four common classes. The obtained results compared with the existing approaches demonstrate the superior performance of the proposed approach.