Fingerprint Clustering and its Application to Generate Class Code Using ART Neural Network

In this paper, we present a novel approach to group fingerprints according to its minutiae point's locations. Our technique for grouping fingerprints is based on the ART1 neural network. We compare the quality of clustering of our ART1 based clustering technique with that of the self organizing neural network (SOM) clustering algorithm in terms of intra-cluster distances. Our results show that the average intra-cluster distance of the clusters formed by SOM algorithm varies from 45.689 to 210.895, while the average intra-cluster distance of clusters formed by our ART1 based clustering technique is almost constant (approximately 24.219), which indicates the high quality of clusters formed by our approach. We present a fingerprint class-code generation scheme in which we apply our clustering technique to group fingerprints that can make fingerprint recognition process faster.